Compare commits
8 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 9d0e1f64d4 | |||
| e180baf776 | |||
| 3d71db4958 | |||
| 2a211992d4 | |||
| a084feb812 | |||
| 64e870c207 | |||
| 19abc599ec | |||
| beddf9acc2 |
@@ -0,0 +1,166 @@
|
||||
name: El SDK Release
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
build-and-release:
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install build dependencies
|
||||
run: |
|
||||
apt-get update -qq
|
||||
apt-get install -y gcc libcurl4-openssl-dev
|
||||
|
||||
# Gen2: compile the bootstrap C source into a working elc binary
|
||||
- name: Build elc from bootstrap (gen2)
|
||||
run: |
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-bootstrap.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread \
|
||||
-o dist/elc-gen2
|
||||
chmod +x dist/elc-gen2
|
||||
echo "gen2 elc built"
|
||||
dist/elc-gen2 --version || true
|
||||
|
||||
# Gen3: use gen2 to compile the El compiler from its own El source (self-host)
|
||||
- name: Self-host: compile El compiler with gen2 (gen3)
|
||||
run: |
|
||||
mkdir -p dist/platform
|
||||
dist/elc-gen2 el-compiler/src/compiler.el > dist/elc-gen3.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-gen3.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread \
|
||||
-o dist/platform/elc
|
||||
chmod +x dist/platform/elc
|
||||
echo "gen3 (self-hosted) elc built"
|
||||
dist/platform/elc --version || true
|
||||
|
||||
# Run all four test suites with gen3 elc
|
||||
- name: Run tests — text
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/text/run.sh
|
||||
|
||||
- name: Run tests — calendar
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/calendar/run.sh
|
||||
|
||||
- name: Run tests — time
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/time/run.sh
|
||||
|
||||
- name: Run tests — html_sanitizer
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/html_sanitizer/run.sh
|
||||
|
||||
# Publish / update the `latest` release with the three SDK assets
|
||||
- name: Publish latest release
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_API: https://git.neuralplatform.ai/api/v1
|
||||
REPO: neuron-technologies/el
|
||||
run: |
|
||||
# Delete existing `latest` release if it exists
|
||||
EXISTING_ID=$(curl -sf \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
"${GITEA_API}/repos/${REPO}/releases/tags/latest" \
|
||||
| python3 -c "import sys,json; d=json.load(sys.stdin); print(d['id'])" 2>/dev/null || true)
|
||||
|
||||
if [ -n "${EXISTING_ID}" ]; then
|
||||
echo "Deleting existing release id=${EXISTING_ID}"
|
||||
curl -sf -X DELETE \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
"${GITEA_API}/repos/${REPO}/releases/${EXISTING_ID}"
|
||||
fi
|
||||
|
||||
# Delete and re-create the `latest` tag so it points at HEAD
|
||||
curl -sf -X DELETE \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
"${GITEA_API}/repos/${REPO}/tags/latest" || true
|
||||
|
||||
# Create the release
|
||||
RELEASE_ID=$(curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
"${GITEA_API}/repos/${REPO}/releases" \
|
||||
-d "{
|
||||
\"tag_name\": \"latest\",
|
||||
\"name\": \"El SDK (latest)\",
|
||||
\"body\": \"Latest El SDK build from commit ${GITHUB_SHA}.\nBuilt $(date -u +%Y-%m-%dT%H:%M:%SZ).\",
|
||||
\"draft\": false,
|
||||
\"prerelease\": false
|
||||
}" | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
|
||||
|
||||
echo "Created release id=${RELEASE_ID}"
|
||||
|
||||
# Upload assets
|
||||
upload_asset() {
|
||||
local filepath="$1"
|
||||
local name="$2"
|
||||
echo "Uploading ${name}..."
|
||||
curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-F "attachment=@${filepath};filename=${name}" \
|
||||
"${GITEA_API}/repos/${REPO}/releases/${RELEASE_ID}/assets"
|
||||
}
|
||||
|
||||
upload_asset dist/platform/elc elc
|
||||
upload_asset el-compiler/runtime/el_runtime.c el_runtime.c
|
||||
upload_asset el-compiler/runtime/el_runtime.h el_runtime.h
|
||||
|
||||
echo "Release published successfully"
|
||||
|
||||
# Dispatch el-sdk-updated event to downstream repos
|
||||
- name: Dispatch to foundation/engram
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_API: https://git.neuralplatform.ai/api/v1
|
||||
run: |
|
||||
curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
"${GITEA_API}/repos/neuron-technologies/engram/dispatches" \
|
||||
-d "{
|
||||
\"type\": \"el-sdk-updated\",
|
||||
\"inputs\": {
|
||||
\"el_version\": \"latest\",
|
||||
\"commit\": \"${GITHUB_SHA}\"
|
||||
}
|
||||
}"
|
||||
echo "Dispatched el-sdk-updated to foundation/engram"
|
||||
|
||||
- name: Dispatch to neuron-technologies/forge
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_API: https://git.neuralplatform.ai/api/v1
|
||||
run: |
|
||||
curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
"${GITEA_API}/repos/neuron-technologies/forge/dispatches" \
|
||||
-d "{
|
||||
\"type\": \"el-sdk-updated\",
|
||||
\"inputs\": {
|
||||
\"el_version\": \"latest\",
|
||||
\"commit\": \"${GITHUB_SHA}\"
|
||||
}
|
||||
}"
|
||||
echo "Dispatched el-sdk-updated to neuron-technologies/forge"
|
||||
+979
@@ -0,0 +1,979 @@
|
||||
# El Language Bootstrap Guide
|
||||
|
||||
This document is the authoritative guide for reconstructing the El compiler toolchain from scratch. If the bootstrap binary at `dist/platform/elc` is ever lost, this document is the path back.
|
||||
|
||||
---
|
||||
|
||||
## 1. The Bootstrap Chain (Current State)
|
||||
|
||||
### The Trust Chain
|
||||
|
||||
El is a self-hosting language. The compiler is written in El. This creates a circular dependency: you need an El compiler to compile the El compiler. The chain is resolved by a seed binary:
|
||||
|
||||
```
|
||||
dist/platform/elc (Mach-O arm64 native binary)
|
||||
↓
|
||||
compiles elc-cli.el
|
||||
↓
|
||||
new self-hosted elc binary
|
||||
↓
|
||||
compiles itself again (identity check)
|
||||
↓
|
||||
stable self-hosted compiler
|
||||
```
|
||||
|
||||
The binary at `dist/platform/elc` is a **Mach-O 64-bit arm64 executable**. The `elc.preselfhost` and `elc.legacy` files in the same directory are older snapshots kept as fallback checkpoints.
|
||||
|
||||
The key property: every binary in `dist/platform/` was produced by compiling the El source in `el-compiler/src/` using a previous version of that same binary. The chain is auditable: the source is the ground truth, not the binary.
|
||||
|
||||
### The Self-Hosting Pipeline
|
||||
|
||||
```
|
||||
elc-cli.el
|
||||
imports → el-compiler/src/compiler.el
|
||||
imports → el-compiler/src/lexer.el
|
||||
imports → el-compiler/src/parser.el
|
||||
imports → el-compiler/src/codegen.el
|
||||
imports → el-compiler/src/codegen-js.el
|
||||
```
|
||||
|
||||
Import resolution is textual. `compiler.el` recursively inlines all imported `.el` files before lex/parse. The result is one large unified source string that the compiler then processes in a single pass.
|
||||
|
||||
`elc-combined.el` in the repo root is a pre-merged single-file edition used during early bootstrap iterations.
|
||||
|
||||
### What the Bootstrap Binary Actually Is
|
||||
|
||||
The `dist/platform/elc` binary is a compiled El program that was produced by running an earlier version of itself on `elc-cli.el`. It is not a Rust binary. The `elc.legacy` and `elc.preselfhost` checkpoints suggest the chain has been continuously self-hosting and re-stamped. The original genesis compiler (referenced in the language spec as a "Rust genesis compiler") was used to produce the first self-hosted binary; that Rust binary is not present in this repo.
|
||||
|
||||
To rebuild the current binary from source using the current binary:
|
||||
|
||||
```bash
|
||||
cd /path/to/el
|
||||
./dist/platform/elc elc-cli.el elc-new.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o dist/platform/elc-new \
|
||||
elc-new.c el-compiler/runtime/el_runtime.c
|
||||
```
|
||||
|
||||
Verify self-hosting by using `elc-new` to recompile itself and diffing the outputs.
|
||||
|
||||
---
|
||||
|
||||
## 2. The Language
|
||||
|
||||
### 2.1 Lexical Structure
|
||||
|
||||
El source is UTF-8. File extension `.el`. Comments are single-line only: `//` to end of line.
|
||||
|
||||
**Token representation:** every token is a map `{ "kind": String, "value": String }`.
|
||||
|
||||
**Keywords** — from `keyword_kind()` in `lexer.el`:
|
||||
|
||||
| Keyword | Token Kind | Notes |
|
||||
|---------|-----------|-------|
|
||||
| `let` | `Let` | variable binding |
|
||||
| `fn` | `Fn` | function definition |
|
||||
| `type` | `Type` | struct definition |
|
||||
| `enum` | `Enum` | enum definition |
|
||||
| `match` | `Match` | pattern match |
|
||||
| `return` | `Return` | function return |
|
||||
| `if` | `If` | conditional |
|
||||
| `else` | `Else` | |
|
||||
| `for` | `For` | iteration |
|
||||
| `in` | `In` | used in `for x in list` |
|
||||
| `while` | `While` | loop |
|
||||
| `import` | `Import` | module import |
|
||||
| `from` | `From` | `from mod import { Name }` |
|
||||
| `as` | `As` | (reserved, no parse form) |
|
||||
| `with` | `With` | (reserved) |
|
||||
| `sealed` | `Sealed` | (reserved) |
|
||||
| `activate` | `Activate` | (reserved) |
|
||||
| `where` | `Where` | (reserved) |
|
||||
| `test` | `Test` | (reserved) |
|
||||
| `seed` | `Seed` | (reserved) |
|
||||
| `assert` | `Assert` | (reserved) |
|
||||
| `protocol` | `Protocol` | (reserved) |
|
||||
| `impl` | `Impl` | (reserved) |
|
||||
| `retry` | `Retry` | reserved / soft keyword in expr position |
|
||||
| `times` | `Times` | reserved / soft keyword |
|
||||
| `fallback` | `Fallback` | reserved / soft keyword |
|
||||
| `reason` | `Reason` | reserved / soft keyword |
|
||||
| `parallel` | `Parallel` | reserved / soft keyword |
|
||||
| `trace` | `Trace` | reserved / soft keyword |
|
||||
| `requires` | `Requires` | reserved / soft keyword |
|
||||
| `deploy` | `Deploy` | reserved / soft keyword |
|
||||
| `to` | `To` | reserved / soft keyword |
|
||||
| `via` | `Via` | reserved / soft keyword |
|
||||
| `target` | `Target` | **RESERVED — cannot use as identifier** |
|
||||
| `true` | `Bool` | literal value `true` |
|
||||
| `false` | `Bool` | literal value `false` |
|
||||
| `cgi` | `Cgi` | CGI identity block |
|
||||
| `service` | `Service` | service declaration block |
|
||||
| `manager` | `Manager` | VBD role decorator / soft keyword |
|
||||
| `engine` | `Engine` | VBD role decorator / soft keyword |
|
||||
| `accessor` | `Accessor` | VBD role decorator / soft keyword |
|
||||
| `vessel` | `Vessel` | soft keyword |
|
||||
| `extern` | `Extern` | `extern fn` forward declaration |
|
||||
|
||||
**Soft keywords** (`target`, `to`, `via`, `deploy`, `reason`, `times`, `fallback`, `retry`, `parallel`, `trace`, `requires`, `where`, `as`, `with`, `manager`, `engine`, `accessor`, `vessel`): these have dedicated token kinds but the parser re-interprets them as `Ident` nodes when they appear in expression position (e.g., as parameter names or local variable names).
|
||||
|
||||
**All token kinds:**
|
||||
|
||||
| Kind | Pattern |
|
||||
|------|---------|
|
||||
| `Int` | `[0-9]+` |
|
||||
| `Float` | `[0-9]+ '.' [0-9]+` |
|
||||
| `Str` | `"…"` with `\"`, `\n`, `\t`, `\r`, `\\` escapes |
|
||||
| `Bool` | `true` or `false` |
|
||||
| `Ident` | `[a-zA-Z_][a-zA-Z0-9_]*` (not a keyword) |
|
||||
| keyword tokens | one per keyword above |
|
||||
| `Eq` | `=` |
|
||||
| `EqEq` | `==` |
|
||||
| `NotEq` | `!=` |
|
||||
| `Not` | `!` |
|
||||
| `Lt` / `LtEq` / `Gt` / `GtEq` | `<` `<=` `>` `>=` |
|
||||
| `And` | `&&` (single `&` is consumed and discarded) |
|
||||
| `Or` | `\|\|` |
|
||||
| `Pipe` | `\|` |
|
||||
| `PipeOp` | `\|>` |
|
||||
| `Plus` / `Minus` / `Star` / `Slash` | `+` `-` `*` `/` |
|
||||
| `Percent` | `%` |
|
||||
| `Arrow` | `->` |
|
||||
| `FatArrow` | `=>` |
|
||||
| `Colon` / `ColonColon` | `:` `::` |
|
||||
| `LParen` / `RParen` | `(` `)` |
|
||||
| `LBrace` / `RBrace` | `{` `}` |
|
||||
| `LBracket` / `RBracket` | `[` `]` |
|
||||
| `Comma` / `Dot` / `Semicolon` | `,` `.` `;` |
|
||||
| `At` | `@` |
|
||||
| `QuestionMark` | `?` |
|
||||
| `Eof` | end-of-input sentinel |
|
||||
|
||||
**String comment stripping:** the lexer contains a special heuristic for string literals that embed JavaScript or CSS (`looks_like_code`). If a string contains `<script`, `<style`, or `function` + `;`, the lexer strips `//` and `/* */` comments from the string value before producing the `Str` token. This is a compile-time content sanitization pass.
|
||||
|
||||
### 2.2 AST Node Types
|
||||
|
||||
Every AST node is a `Map<String, Any>`. The `"expr"` or `"stmt"` key names the node type.
|
||||
|
||||
**Expression nodes:**
|
||||
|
||||
| `expr` value | Fields | Meaning |
|
||||
|-------------|--------|---------|
|
||||
| `Int` | `value: String` | integer literal |
|
||||
| `Float` | `value: String` | float literal |
|
||||
| `Str` | `value: String` | string literal |
|
||||
| `Bool` | `value: String` | `"true"` or `"false"` |
|
||||
| `Nil` | — | null / missing |
|
||||
| `Ident` | `name: String` | identifier reference |
|
||||
| `BinOp` | `op: String`, `left`, `right` | binary operation |
|
||||
| `Not` | `inner` | unary `!` |
|
||||
| `Neg` | `inner` | unary `-` |
|
||||
| `Call` | `func`, `args: [expr]` | function call |
|
||||
| `Field` | `object`, `field: String` | `obj.field` |
|
||||
| `Index` | `object`, `index` | `obj[idx]` |
|
||||
| `Array` | `elems: [expr]` | `[e1, e2, …]` |
|
||||
| `Map` | `pairs: [{ key: String, value: expr }]` | `{ "k": v, … }` |
|
||||
| `If` | `cond`, `then: [stmt]`, `else: [stmt]`, `has_else: Bool` | conditional expression |
|
||||
| `For` | `item: String`, `list`, `body: [stmt]` | for-in expression |
|
||||
| `Match` | `subject`, `arms: [{ pattern, body }]` | pattern match |
|
||||
| `DurationLit` | `count: String`, `unit: String` | `30.seconds`, `1.hour` |
|
||||
| `Try` | `inner` | postfix `?` (no-op passthrough today) |
|
||||
|
||||
**Binary operators** (`op` field values): `Plus`, `Minus`, `Star`, `Slash`, `EqEq`, `NotEq`, `Lt`, `Gt`, `LtEq`, `GtEq`, `And`, `Or`.
|
||||
|
||||
**Operator precedence** (higher = tighter binding):
|
||||
|
||||
| Level | Operators |
|
||||
|-------|-----------|
|
||||
| 6 | `Star`, `Slash` |
|
||||
| 5 | `Plus`, `Minus` |
|
||||
| 4 | `Lt`, `Gt`, `LtEq`, `GtEq` |
|
||||
| 3 | `EqEq`, `NotEq` |
|
||||
| 2 | `And` |
|
||||
| 1 | `Or` |
|
||||
|
||||
**Pattern nodes** (used inside `Match` arms):
|
||||
|
||||
| `pattern` value | Fields | Meaning |
|
||||
|----------------|--------|---------|
|
||||
| `Wildcard` | — | `_` — always matches |
|
||||
| `Binding` | `name: String` | binds subject to name |
|
||||
| `LitInt` | `value: String` | integer literal pattern |
|
||||
| `LitStr` | `value: String` | string literal pattern |
|
||||
| `LitBool` | `value: String` | boolean literal pattern |
|
||||
|
||||
**Statement nodes:**
|
||||
|
||||
| `stmt` value | Fields | Meaning |
|
||||
|-------------|--------|---------|
|
||||
| `Let` | `name: String`, `value: expr`, `type: String` | variable binding |
|
||||
| `Assign` | `name: String`, `value: expr` | bare reassignment `name = expr` |
|
||||
| `Return` | `value: expr` | return statement |
|
||||
| `While` | `cond: expr`, `body: [stmt]` | while loop |
|
||||
| `For` | `item: String`, `list: expr`, `body: [stmt]` | for-in loop |
|
||||
| `FnDef` | `name: String`, `params: [param]`, `body: [stmt]`, `ret_type: String`, `decorator?: String` | function definition |
|
||||
| `ExternFn` | `name: String`, `params: [param]`, `ret_type: String` | forward declaration |
|
||||
| `TypeDef` | `name: String`, `fields: [{ name: String }]` | struct type definition |
|
||||
| `EnumDef` | `name: String`, `variants: [{ name: String }]` | enum definition |
|
||||
| `Import` | `path: String` | `import "file.el"` or `from mod import { … }` |
|
||||
| `CgiBlock` | `name`, `dharma_id`, `principal`, `network`, `engram`, `has_*: Bool` | CGI identity declaration |
|
||||
| `ServiceBlock` | `name`, `sponsor`, `domain` | service declaration |
|
||||
| `Expr` | `value: expr` | bare expression statement |
|
||||
|
||||
**Param nodes:** `{ "name": String, "type": String }` where `type` is the leading identifier of the type annotation (e.g., `"Int"`, `"String"`, `"Map"`) or `""` if unannotated.
|
||||
|
||||
### 2.3 The Type System
|
||||
|
||||
Type annotations are parsed and stored but not type-checked at compile time. They serve as documentation and as hints to the codegen for arithmetic dispatch.
|
||||
|
||||
**Built-in types:**
|
||||
|
||||
| Type | C representation | Notes |
|
||||
|------|-----------------|-------|
|
||||
| `String` | `const char*` cast to `el_val_t` | via `EL_STR()` macro |
|
||||
| `Int` | `int64_t` | direct |
|
||||
| `Bool` | `int64_t` | `0` = false, nonzero = true |
|
||||
| `Float` | `int64_t` | bit-cast double via `el_from_float()` |
|
||||
| `Void` | `void` | functions returning nothing |
|
||||
| `Any` | `void*` cast to `el_val_t` | generic containers |
|
||||
| `[T]` | `el_val_t` | pointer to ElList struct |
|
||||
| `Map<K,V>` | `el_val_t` | pointer to ElMap struct |
|
||||
|
||||
**Temporal types** (first-class in codegen):
|
||||
|
||||
| Type | Representation | Notes |
|
||||
|------|---------------|-------|
|
||||
| `Instant` | nanoseconds since Unix epoch as `int64_t` | `now()` returns this |
|
||||
| `Duration` | signed nanoseconds as `int64_t` | `30.seconds` = `30 * 1000000000` |
|
||||
| `Calendar` | pointer to heap-allocated struct | `earth_calendar(zone)` |
|
||||
| `CalendarTime` | pointer to heap-allocated struct | `now_in(cal)` |
|
||||
| `LocalDate` | pointer to heap-allocated struct | `local_date(y, m, d)` |
|
||||
| `LocalTime` | nanoseconds since midnight, direct `int64_t` | `local_time(h, m, s, ns)` |
|
||||
| `Zone` | pointer to heap-allocated struct | `zone("America/New_York")` |
|
||||
| `Rhythm` | pointer to heap-allocated struct | recurrence pattern |
|
||||
|
||||
The codegen tracks type-annotated variable names in per-function process state (`__int_names`, `__instant_names`, `__duration_names`, etc.) to dispatch arithmetic and comparisons through the correct runtime wrappers. Type-mismatched operations (e.g., `Instant + Instant`) are emitted as `#error` directives.
|
||||
|
||||
**Duration postfix literals:** `30.seconds`, `1.hour`, `500.millis`, `30.nanos` are parsed as `DurationLit` AST nodes and compiled to `el_duration_from_nanos(count * multiplier)`. The multipliers:
|
||||
|
||||
| Unit | Nanoseconds |
|
||||
|------|------------|
|
||||
| `nano` / `nanos` | 1 |
|
||||
| `milli` / `millis` / `millisecond` / `milliseconds` | 1,000,000 |
|
||||
| `second` / `seconds` | 1,000,000,000 |
|
||||
| `minute` / `minutes` | 60,000,000,000 |
|
||||
| `hour` / `hours` | 3,600,000,000,000 |
|
||||
| `day` / `days` | 86,400,000,000,000 |
|
||||
|
||||
### 2.4 Key Language Semantics
|
||||
|
||||
**Implicit return.** The final expression in a function body becomes the return value if it is not a control-flow construct (`If`, `For`). The codegen's `transform_implicit_return` rewrites the last `Expr` statement into a `Return` statement before emitting.
|
||||
|
||||
**Let-rebinding, not mutation.** El uses `let` for both initial binding and rebinding:
|
||||
```el
|
||||
let count = 0
|
||||
let count = count + 1 // NOT mutation — creates a new binding in the same scope
|
||||
```
|
||||
The codegen tracks declared names per C scope. When `count` is already in `declared`, it emits `count = count + 1;` (plain assignment). When it is new, it emits `el_val_t count = 0;`. This means **El does not have mutable variables in the traditional sense** — every `let` is a potential redeclaration. The practical effect is that shadowing and in-place update use identical syntax.
|
||||
|
||||
**Bare reassignment.** The parser also handles `name = expr` (without `let`) when an `Ident` is immediately followed by `Eq`. This emits a plain C assignment.
|
||||
|
||||
**`target` is reserved.** The word `target` is lexed as the `Target` token kind — it cannot be used as a variable or parameter name. Use `tgt` or another name instead. This is a live gotcha in `compiler.el` itself, which uses `tgt` for exactly this reason.
|
||||
|
||||
**`__no_block_expr` guard.** The parser uses process state key `__no_block_expr` to suppress Map-literal parsing when parsing the condition of `if`, `while`, `for`, and `match`. This prevents a stray `{` (the start of the then-block) from being parsed as a Map literal.
|
||||
|
||||
**Arena memory model.** The runtime includes an arena allocator that is activated in server/long-running contexts. In CLI mode (`elc`, `elb`) the arena is inactive. Memory is managed via ARC (reference counting): `el_retain()` and `el_release()` on Lists and Maps. Strings and ints are not refcounted — the retain/release functions are safe no-ops on non-tagged values.
|
||||
|
||||
---
|
||||
|
||||
## 3. The Runtime API
|
||||
|
||||
All runtime functions are declared in `el-compiler/runtime/el_runtime.h`. Every compiled El program links against `el-compiler/runtime/el_runtime.c`.
|
||||
|
||||
All values are `el_val_t` (`int64_t`). Strings are pointers cast through `int64_t` using `EL_STR(s)` / `EL_CSTR(v)` macros.
|
||||
|
||||
Canonical compile command:
|
||||
```bash
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
```
|
||||
|
||||
### I/O
|
||||
|
||||
| Function | Signature | Description |
|
||||
|----------|-----------|-------------|
|
||||
| `println` | `(s) -> Void` | print string + newline to stdout |
|
||||
| `print` | `(s) -> Void` | print string without newline |
|
||||
| `readline` | `() -> String` | read one line from stdin |
|
||||
|
||||
### String Operations
|
||||
|
||||
| Function | Signature | Description |
|
||||
|----------|-----------|-------------|
|
||||
| `el_str_concat` | `(a, b) -> String` | concatenate two strings |
|
||||
| `str_concat` | `(a, b) -> String` | alias for `el_str_concat` |
|
||||
| `str_eq` | `(a, b) -> Bool` | string equality comparison |
|
||||
| `str_starts_with` | `(s, prefix) -> Bool` | prefix test |
|
||||
| `str_ends_with` | `(s, suffix) -> Bool` | suffix test |
|
||||
| `str_contains` | `(s, sub) -> Bool` | substring test |
|
||||
| `str_len` | `(s) -> Int` | byte length |
|
||||
| `str_slice` | `(s, start, end) -> String` | substring (byte offsets) |
|
||||
| `str_replace` | `(s, from, to) -> String` | replace all occurrences |
|
||||
| `str_to_upper` / `str_upper` | `(s) -> String` | uppercase |
|
||||
| `str_to_lower` / `str_lower` | `(s) -> String` | lowercase |
|
||||
| `str_trim` | `(s) -> String` | strip leading/trailing whitespace |
|
||||
| `str_lstrip` / `str_rstrip` | `(s) -> String` | one-sided strip |
|
||||
| `str_index_of` | `(s, sub) -> Int` | position of substring; `-1` if absent |
|
||||
| `str_last_index_of` | `(s, sub) -> Int` | last position |
|
||||
| `str_index_of_all` | `(s, sub) -> [Int]` | all byte offsets (non-overlapping) |
|
||||
| `str_find_chars` | `(s, any_of) -> Int` | first index of any char in set |
|
||||
| `str_split` | `(s, sep) -> [String]` | split on separator |
|
||||
| `str_split_lines` | `(s) -> [String]` | split on newlines |
|
||||
| `str_split_chars` | `(s) -> [String]` | split into individual characters |
|
||||
| `str_split_n` | `(s, sep, n) -> [String]` | split at most `n` times |
|
||||
| `str_join` | `(list, sep) -> String` | join list with separator |
|
||||
| `str_char_at` | `(s, i) -> String` | character at byte index |
|
||||
| `str_char_code` | `(s, i) -> Int` | Unicode code point at index |
|
||||
| `str_pad_left` | `(s, width, pad) -> String` | left-pad to width |
|
||||
| `str_pad_right` | `(s, width, pad) -> String` | right-pad to width |
|
||||
| `str_format` | `(fmt, data) -> String` | `{key}` interpolation |
|
||||
| `str_repeat` | `(s, n) -> String` | repeat string n times |
|
||||
| `str_reverse` | `(s) -> String` | reverse by codepoint |
|
||||
| `str_strip_prefix` | `(s, prefix) -> String` | remove prefix if present |
|
||||
| `str_strip_suffix` | `(s, suffix) -> String` | remove suffix if present |
|
||||
| `str_strip_chars` | `(s, chars) -> String` | strip characters from both ends |
|
||||
| `str_count` | `(s, sub) -> Int` | count non-overlapping occurrences |
|
||||
| `str_count_chars` | `(s) -> Int` | codepoint count |
|
||||
| `str_count_bytes` | `(s) -> Int` | alias for `str_len` |
|
||||
| `str_count_lines` | `(s) -> Int` | line count |
|
||||
| `str_count_words` | `(s) -> Int` | word count |
|
||||
| `str_count_letters` | `(s) -> Int` | ASCII letter count |
|
||||
| `str_count_digits` | `(s) -> Int` | ASCII digit count |
|
||||
| `is_letter` / `is_digit` / `is_alphanumeric` | `(s) -> Bool` | ASCII char classification |
|
||||
| `is_whitespace` / `is_punctuation` | `(s) -> Bool` | |
|
||||
| `is_uppercase` / `is_lowercase` | `(s) -> Bool` | |
|
||||
| `int_to_str` | `(n) -> String` | format integer |
|
||||
| `str_to_int` | `(s) -> Int` | parse integer |
|
||||
| `str_to_float` | `(s) -> Float` | parse float |
|
||||
| `parse_int` | `(s, default) -> Int` | parse with fallback |
|
||||
| `bool_to_str` | `(b) -> String` | format bool |
|
||||
|
||||
### Integer/Float Math
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `el_abs(n)` | absolute value |
|
||||
| `el_max(a, b)` | maximum |
|
||||
| `el_min(a, b)` | minimum |
|
||||
| `float_to_str(f)` | format float as string |
|
||||
| `int_to_float(n)` | widen Int to Float |
|
||||
| `float_to_int(f)` | truncate Float to Int |
|
||||
| `format_float(f, decimals)` | format with N decimal places |
|
||||
| `decimal_round(f, decimals)` | round to N decimals |
|
||||
| `math_sqrt(f)` | square root |
|
||||
| `math_log(f)` / `math_ln(f)` | logarithms |
|
||||
| `math_sin(f)` / `math_cos(f)` / `math_pi()` | trigonometry |
|
||||
|
||||
### List Operations
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `el_list_empty()` | create empty list |
|
||||
| `el_list_new(count, …)` | create list from N values (varargs) |
|
||||
| `el_list_len(list)` | length |
|
||||
| `el_list_get(list, i)` | element at index; `0` on out-of-bounds |
|
||||
| `el_list_append(list, e)` | append; returns updated list |
|
||||
| `el_list_clone(list)` | shallow copy |
|
||||
| `list_push(list, e)` | alias for `el_list_append` |
|
||||
| `list_push_front(list, e)` | prepend |
|
||||
| `list_join(list, sep)` | join to string |
|
||||
| `list_range(start, end)` | integer range `[start, end)` |
|
||||
| `native_list_empty()` | alias for `el_list_empty` (used in compiler source) |
|
||||
| `native_list_append(l, v)` | alias for `el_list_append` |
|
||||
| `native_list_get(l, idx)` | alias for `el_list_get` |
|
||||
| `native_list_len(l)` | alias for `el_list_len` |
|
||||
| `native_list_clone(l)` | alias for `el_list_clone` |
|
||||
| `append(l, e)` | method-call alias: `list.append(e)` |
|
||||
| `len(l)` | method-call alias: `list.len()` |
|
||||
| `get(l, i)` | method-call alias: `list.get(i)` |
|
||||
|
||||
### Map Operations
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `el_map_new(count, …)` | create map from key/value pairs (varargs) |
|
||||
| `el_map_get(map, key)` | get value by key |
|
||||
| `el_map_set(map, key, value)` | set key; returns map |
|
||||
| `el_get_field(map, key)` | alias; emitted for `.field` access |
|
||||
| `map_get(map, key)` | method-call alias |
|
||||
| `map_set(map, key, value)` | method-call alias |
|
||||
|
||||
### ARC (Reference Counting)
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `el_retain(v)` | increment refcount; no-op for non-heap values |
|
||||
| `el_release(v)` | decrement refcount; free when zero |
|
||||
|
||||
### In-Process State
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `state_set(key, value)` | store in process-global key/value table |
|
||||
| `state_get(key)` | retrieve; `""` if absent |
|
||||
| `state_del(key)` | delete key |
|
||||
| `state_keys()` | all keys as `[String]` |
|
||||
|
||||
### Filesystem
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `fs_read(path)` | read file to string; `""` on error |
|
||||
| `fs_write(path, content)` | write string; returns `1` on success |
|
||||
| `fs_write_bytes(path, bytes, length)` | write raw bytes of known length |
|
||||
| `fs_list(path)` | list directory entries |
|
||||
| `fs_exists(path)` | check if path exists |
|
||||
| `fs_mkdir(path)` | mkdir -p |
|
||||
|
||||
### HTTP Client
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `http_get(url)` | GET; returns body string |
|
||||
| `http_post(url, body)` | POST; returns body string |
|
||||
| `http_post_json(url, json_body)` | POST with Content-Type: application/json |
|
||||
| `http_get_with_headers(url, headers_map)` | GET with custom headers |
|
||||
| `http_post_with_headers(url, body, headers_map)` | POST with custom headers |
|
||||
| `http_post_form_auth(url, form_body, auth_header)` | POST with auth |
|
||||
| `http_delete(url)` | DELETE |
|
||||
| `http_get_to_file(url, headers_map, output_path)` | stream response to file |
|
||||
| `http_post_to_file(url, body, headers_map, output_path)` | stream POST response to file |
|
||||
| `http_response(status, headers_json, body)` | build response envelope |
|
||||
| `url_encode(s)` | RFC 3986 percent-encoding |
|
||||
| `url_decode(s)` | URL decode |
|
||||
| `el_html_sanitize(html, allowlist_json)` | allowlist HTML sanitizer |
|
||||
|
||||
### HTTP Server
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `http_serve(port, handler)` | start server; handler: `(method, path, body) -> String` |
|
||||
| `http_serve_v2(port, handler)` | start server; handler: `(method, path, headers_map, body) -> String` |
|
||||
| `http_set_handler(name)` | set handler by symbol name |
|
||||
| `http_set_handler_v2(name)` | v2 variant |
|
||||
|
||||
### JSON
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `json_get(json, key)` | substring lookup of `"key": value` |
|
||||
| `json_parse(s)` | parse JSON string to List/Map |
|
||||
| `json_stringify(v)` | serialize Any to JSON string |
|
||||
| `json_get_string(j, key)` | typed extract: String |
|
||||
| `json_get_int(j, key)` | typed extract: Int |
|
||||
| `json_get_float(j, key)` | typed extract: Float |
|
||||
| `json_get_bool(j, key)` | typed extract: Bool |
|
||||
| `json_get_raw(j, key)` | extract nested object/array as JSON string |
|
||||
| `json_set(j, key, value)` | update field, return new JSON string |
|
||||
| `json_array_len(j)` | length of JSON array string |
|
||||
| `json_array_get(j, index)` | element at index |
|
||||
| `json_array_get_string(j, index)` | string element at index |
|
||||
|
||||
### Time (Epoch-Based)
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `time_now()` | Unix epoch milliseconds |
|
||||
| `time_now_utc()` | same, explicit UTC |
|
||||
| `time_format(ts, fmt)` | format timestamp |
|
||||
| `time_to_parts(ts)` | decompose to Map of fields |
|
||||
| `time_from_parts(secs, ns, tz)` | construct timestamp |
|
||||
| `time_add(ts, n, unit)` | add duration |
|
||||
| `time_diff(ts1, ts2, unit)` | difference |
|
||||
| `unix_timestamp()` | Unix seconds as Int |
|
||||
| `sleep_secs(secs)` | sleep N seconds |
|
||||
| `sleep_ms(ms)` | sleep N milliseconds |
|
||||
|
||||
### Time (First-Class Instant/Duration)
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `now()` / `el_now_instant()` | current time as Instant (nanoseconds) |
|
||||
| `unix_seconds(n)` | construct Instant from Unix seconds |
|
||||
| `unix_millis(n)` | construct Instant from Unix milliseconds |
|
||||
| `instant_from_iso8601(s)` | parse ISO 8601 string |
|
||||
| `instant_to_unix_seconds(i)` | extract Unix seconds |
|
||||
| `instant_to_unix_millis(i)` | extract Unix milliseconds |
|
||||
| `instant_to_iso8601(i)` | format as ISO 8601 |
|
||||
| `el_duration_from_nanos(ns)` | construct Duration from nanoseconds |
|
||||
| `duration_seconds(n)` | Duration from seconds |
|
||||
| `duration_millis(n)` | Duration from milliseconds |
|
||||
| `duration_nanos(n)` | Duration from nanoseconds |
|
||||
| `duration_to_seconds(d)` | extract seconds |
|
||||
| `duration_to_millis(d)` | extract milliseconds |
|
||||
| `duration_to_nanos(d)` | extract nanoseconds |
|
||||
| `el_instant_add_dur(inst, dur)` | Instant + Duration |
|
||||
| `el_instant_sub_dur(inst, dur)` | Instant - Duration |
|
||||
| `el_instant_diff(a, b)` | Instant - Instant = Duration |
|
||||
| `el_duration_add/sub/scale/div` | Duration arithmetic |
|
||||
| `el_instant_lt/le/gt/ge/eq/ne` | Instant comparison |
|
||||
| `el_duration_lt/le/gt/ge/eq/ne` | Duration comparison |
|
||||
| `el_sleep_duration(dur)` | sleep for a Duration |
|
||||
| `ttl_cache_set(key, value)` | store with TTL |
|
||||
| `ttl_cache_get(key, max_age)` | retrieve if within max_age |
|
||||
| `ttl_cache_age(key)` | age of cached value as Duration |
|
||||
|
||||
### Calendar System
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `zone(id)` | IANA zone or fixed offset |
|
||||
| `zone_utc()` / `zone_local()` | UTC and local zone |
|
||||
| `zone_offset(hours, minutes)` | fixed offset zone |
|
||||
| `earth_calendar(z)` | Gregorian calendar in zone |
|
||||
| `earth_calendar_default()` | system default |
|
||||
| `mars_calendar()` / `cycle_calendar(period)` | non-Earth calendars |
|
||||
| `no_cycle_calendar()` / `relative_calendar(epoch)` | abstract calendars |
|
||||
| `now_in(cal)` | current time as CalendarTime |
|
||||
| `in_calendar(inst, cal)` | project Instant into Calendar |
|
||||
| `cal_format(ct, pattern)` | format CalendarTime |
|
||||
| `cal_to_instant(ct)` | extract underlying Instant |
|
||||
| `cal_cycle_phase(ct)` / `cal_in(ct, cal)` | calendar ops |
|
||||
| `local_date(y, m, d)` | construct LocalDate |
|
||||
| `local_time(h, m, s, ns)` | construct LocalTime |
|
||||
| `local_datetime(date, time)` | construct LocalDateTime |
|
||||
| `zoned(date, time, cal)` | zoned datetime |
|
||||
| `local_date_year/month/day` | LocalDate accessors |
|
||||
| `local_time_hour/minute/second/nanos` | LocalTime accessors |
|
||||
| `el_local_date_add_dur` / `el_local_time_add_dur` | date/time arithmetic |
|
||||
| `el_local_date_lt` / `el_local_date_eq` | date comparison |
|
||||
| `rhythm_*` | recurrence patterns (cycle_start, weekday, weekly_at, next_after, matches, …) |
|
||||
|
||||
### Process / Execution
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `args()` | command-line arguments as `[String]` (excludes argv[0]) |
|
||||
| `env(key)` | read environment variable; `""` if unset |
|
||||
| `exit(code)` | exit process with code |
|
||||
| `exit_program(code)` | alias for `exit` |
|
||||
| `getpid_now()` | current process ID |
|
||||
| `exec_command(cmd)` | run shell command; return exit code |
|
||||
| `exec_capture(cmd)` | run shell command; capture and return stdout |
|
||||
| `uuid_new()` / `uuid_v4()` | generate UUID v4 |
|
||||
| `native_int_to_str(n)` | format integer (alias, used in compiler source) |
|
||||
| `native_string_chars(s)` | split string into `[String]` of single characters |
|
||||
|
||||
### Crypto
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `sha256_hex(input)` | SHA-256, hex output |
|
||||
| `sha256_bytes(input)` | SHA-256, raw bytes |
|
||||
| `hmac_sha256_hex(key, msg)` | HMAC-SHA-256, hex |
|
||||
| `hmac_sha256_bytes(key, msg)` | HMAC-SHA-256, raw bytes |
|
||||
| `base64_encode(input)` / `base64_decode(input)` | standard base64 |
|
||||
| `base64url_encode(input)` / `base64url_decode(input)` | URL-safe base64 |
|
||||
| `sha3_256_hex(input)` | SHA3-256 (Keccak) |
|
||||
| `pq_keygen_signature()` | Dilithium-3 key pair |
|
||||
| `pq_sign(sk_hex, msg)` / `pq_verify(pk_hex, msg, sig_hex)` | PQ signatures |
|
||||
| `pq_kem_keygen()` / `pq_kem_encaps(pk)` / `pq_kem_decaps(sk, ct)` | Kyber-768 KEM |
|
||||
| `pq_hybrid_keygen()` / `pq_hybrid_handshake(remote_pub)` | X25519 + Kyber hybrid |
|
||||
| `aead_encrypt(key_hex, plaintext)` | AES-256-GCM encrypt |
|
||||
| `aead_decrypt(key_hex, nonce_hex, ct_hex)` | AES-256-GCM decrypt |
|
||||
|
||||
### DHARMA Network (CGI programs only)
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `el_cgi_init(name, dharma_id, principal, network, engram)` | initialize CGI identity (called by generated `main()`) |
|
||||
| `dharma_connect(cgi_id)` | open channel to peer |
|
||||
| `dharma_send(channel, content)` | send message; blocks for response |
|
||||
| `dharma_activate(query)` | spreading activation across DHARMA network |
|
||||
| `dharma_emit(event_type, payload)` | emit network event (@manager only) |
|
||||
| `dharma_field(event_type)` | wait for event (@manager only) |
|
||||
| `dharma_strengthen(cgi_id, weight)` | Hebbian potentiation |
|
||||
| `dharma_relationship(cgi_id)` | current relationship weight |
|
||||
| `dharma_peers()` | all connected peers sorted by weight |
|
||||
|
||||
### Engram Knowledge Graph
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `engram_node(content, type, salience)` | create node; returns ID |
|
||||
| `engram_node_full(content, type, label, salience, importance, confidence, tier, tags)` | full node creation |
|
||||
| `engram_node_layered(…, layer_id)` | create node in specific layer |
|
||||
| `engram_get_node(id)` | retrieve node by ID |
|
||||
| `engram_strengthen(node_id)` | Hebbian potentiation |
|
||||
| `engram_forget(node_id)` | delete node and edges |
|
||||
| `engram_node_count()` | total node count |
|
||||
| `engram_edge_count()` | total edge count |
|
||||
| `engram_search(query, limit)` | full-text search |
|
||||
| `engram_scan_nodes(limit, offset)` | paginated node scan |
|
||||
| `engram_connect(from, to, weight, relation)` | create directed edge |
|
||||
| `engram_edge_between(from, to)` | get edge |
|
||||
| `engram_neighbors(node_id)` | BFS neighbors |
|
||||
| `engram_neighbors_filtered(node_id, max_depth, direction)` | filtered BFS |
|
||||
| `engram_activate(query, depth)` | spreading activation |
|
||||
| `engram_save(path)` / `engram_load(path)` | snapshot to/from disk |
|
||||
| `engram_add_layer(name, priority, suppressible, transparent, injectable)` | add consciousness layer |
|
||||
| `engram_remove_layer(layer_id)` / `engram_list_layers()` | layer management |
|
||||
| `engram_*_json` variants | JSON-string versions of search/scan/activate |
|
||||
| `engram_compile_layered_json(intent, depth)` | prompt-ready context block |
|
||||
|
||||
### LLM (Anthropic API)
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `llm_call(model, prompt)` | single-turn call |
|
||||
| `llm_call_system(model, system, user)` | call with system prompt |
|
||||
| `llm_call_agentic(model, system, user, tools)` | agentic call with tools (CGI only) |
|
||||
| `llm_vision(model, system, prompt, image)` | vision call |
|
||||
| `llm_models()` | list available models |
|
||||
| `llm_register_tool(name, handler_fn_name)` | register tool handler (CGI only) |
|
||||
|
||||
### Observability
|
||||
|
||||
| Function | Description |
|
||||
|----------|-------------|
|
||||
| `emit_log(level, msg, fields_json)` | emit OTLP log |
|
||||
| `emit_metric(name, value, tags_json)` | emit OTLP metric |
|
||||
| `trace_span_start(name)` | start trace span |
|
||||
| `trace_span_end(span_handle)` | end trace span |
|
||||
| `emit_event(name, duration_ms)` | emit event |
|
||||
|
||||
---
|
||||
|
||||
## 4. How to Re-Bootstrap from Zero
|
||||
|
||||
This section assumes the bootstrap binary is gone. Everything else (source files, runtime) is intact.
|
||||
|
||||
### What You Need to Implement
|
||||
|
||||
A minimal El compiler has three parts: lexer, parser, codegen. Each can be written in any language. The goal is to compile `elc-cli.el` into a working `elc` binary, after which El is self-hosting again.
|
||||
|
||||
### Step 1: Write a Minimal Lexer
|
||||
|
||||
The lexer must produce a list of `{ "kind": String, "value": String }` maps (or equivalent structures). Required token kinds: `Int`, `Float`, `Str`, `Bool`, `Ident`, `Eof`, and all keywords and operators listed in section 2.1.
|
||||
|
||||
The minimal subset needed to compile the compiler itself:
|
||||
- Keywords: `let`, `fn`, `return`, `if`, `else`, `while`, `for`, `in`, `import`, `from`, `true`, `false`, `extern`
|
||||
- Literals: `Int`, `Str`, `Bool`, `Ident`
|
||||
- Operators: `=`, `==`, `!=`, `!`, `<`, `>`, `<=`, `>=`, `&&`, `||`, `+`, `-`, `*`, `/`, `->`, `=>`, `:`, `,`, `.`, `(`, `)`, `{`, `}`, `[`, `]`, `@`, `?`
|
||||
- Special: `Eof`
|
||||
|
||||
The lexer in `lexer.el` walks a char array using `native_list_get` to avoid O(n²) string slicing. A Python implementation can use a simple index into a string. Escapes to handle: `\"`, `\n`, `\t`, `\r`, `\\`.
|
||||
|
||||
### Step 2: Write a Minimal Parser
|
||||
|
||||
The parser is a standard recursive descent parser. It produces AST maps as described in section 2.2.
|
||||
|
||||
The minimal statement forms needed to compile the compiler:
|
||||
- `let name [: Type] = expr`
|
||||
- `fn name(params) [-> Type] { body }`
|
||||
- `extern fn name(params) [-> Type]`
|
||||
- `return expr`
|
||||
- `while cond { body }`
|
||||
- `for item in list { body }`
|
||||
- `if cond { body } [else [if] { body }]`
|
||||
- `import "path"`
|
||||
- `from module import { … }`
|
||||
- `@decorator stmt`
|
||||
- `name = expr` (bare assignment)
|
||||
- bare expression statement
|
||||
|
||||
The minimal expression forms:
|
||||
- Integer, float, string, bool literals
|
||||
- Identifier
|
||||
- Binary operations with the precedence table from section 2.2
|
||||
- Unary `!` and `-`
|
||||
- Function call: `f(a, b, …)`
|
||||
- Method call: `obj.method(args)` (parsed as Call with Field func)
|
||||
- Field access: `obj.field`
|
||||
- Index access: `obj[i]`
|
||||
- Array literal: `[e1, e2, …]`
|
||||
- Map literal: `{ "key": value, … }`
|
||||
- `if` as expression
|
||||
- `match` expression
|
||||
- Postfix `?` (can be a no-op)
|
||||
- Duration literal: `N.unit`
|
||||
|
||||
The `__no_block_expr` guard (section 2.4) is important: without it, `if a || b { ... }` will incorrectly parse `{` as a Map literal.
|
||||
|
||||
### Step 3: Write a Minimal Codegen
|
||||
|
||||
The codegen emits C11 source. Required output structure:
|
||||
|
||||
```c
|
||||
#include <stdint.h>
|
||||
#include <stdlib.h>
|
||||
#include "el_runtime.h"
|
||||
|
||||
// Forward declarations for all non-main functions
|
||||
el_val_t fn_name(el_val_t p1, el_val_t p2);
|
||||
...
|
||||
|
||||
// File-scope let bindings (if any)
|
||||
el_val_t GLOBAL_NAME;
|
||||
|
||||
// Function bodies
|
||||
el_val_t fn_name(el_val_t p1, el_val_t p2) {
|
||||
...
|
||||
return 0;
|
||||
}
|
||||
|
||||
// Entry point
|
||||
int main(int _argc, char** _argv) {
|
||||
el_runtime_init_args(_argc, _argv);
|
||||
...
|
||||
return 0;
|
||||
}
|
||||
```
|
||||
|
||||
Critical codegen rules:
|
||||
|
||||
1. **All values are `el_val_t`**. Every parameter, local variable, and return type is `el_val_t` unless the function has `ret_type == "Void"` (use `void`).
|
||||
|
||||
2. **Let-rebinding**: track declared names per C scope. Emit `el_val_t name = val;` on first occurrence; emit `name = val;` on subsequent occurrences of the same name in the same scope.
|
||||
|
||||
3. **`+` dispatch**: if either operand is a string literal → `el_str_concat(a, b)`. If both are provably integers → `(a + b)`. Default fallback → `el_str_concat`.
|
||||
|
||||
4. **`==` dispatch**: if either operand is a string or identifier → `str_eq(a, b)`. If both are integer literals or provably Int → `(a == b)`.
|
||||
|
||||
5. **String literals**: wrap in `EL_STR("…")` and escape: `\"` → `\\\"`, `\n` → `\\n`, `\t` → `\\t`, `\\` → `\\\\`.
|
||||
|
||||
6. **Map literals**: `el_map_new(N, "k1", v1, "k2", v2, …)`. Empty map: `el_map_new(0)`.
|
||||
|
||||
7. **Array literals**: `el_list_new(N, e1, e2, …)`. Empty: `el_list_empty()`.
|
||||
|
||||
8. **Index access**: string-literal index → `el_get_field(obj, EL_STR("key"))`. Integer index → `el_list_get(obj, idx)`.
|
||||
|
||||
9. **Field access** `obj.field` → `el_get_field(obj, EL_STR("field"))`.
|
||||
|
||||
10. **Method call** `obj.method(args)` → `method(obj, args)`.
|
||||
|
||||
11. **`for item in list`** → emit:
|
||||
```c
|
||||
{ el_val_t _el_lst = <list>; el_val_t _el_len = el_list_len(_el_lst);
|
||||
for (el_val_t _el_i = 0; _el_i < _el_len; _el_i++) {
|
||||
el_val_t item = el_list_get(_el_lst, _el_i);
|
||||
<body>
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
12. **`match`** → GCC/Clang statement expression with `goto`:
|
||||
```c
|
||||
({ el_val_t _s = <subject>; el_val_t _r = 0;
|
||||
if (_s == 42) { _r = <arm_body>; goto _done; }
|
||||
if (str_eq(_s, EL_STR("str"))) { _r = <arm_body>; goto _done; }
|
||||
{ _r = <wildcard_body>; goto _done; }
|
||||
_done:; _r; })
|
||||
```
|
||||
|
||||
13. **`if` as expression** → similarly wrapped in a GCC/Clang statement expression.
|
||||
|
||||
14. **Implicit return**: if the last statement in a function body is a bare `Expr` (not `If` or `For`), emit it as `return <expr>;` instead of `<expr>;`.
|
||||
|
||||
15. **Float literals**: emit as `el_from_float(<value>)`.
|
||||
|
||||
16. **Bool literals**: `true` → `1`, `false` → `0`.
|
||||
|
||||
17. **`fn main()`**: do not emit as a regular `el_val_t` function. Instead, fold its body into C's `int main()` after any top-level statements.
|
||||
|
||||
18. **`extern fn`**: emit only a forward declaration (no body).
|
||||
|
||||
19. **Forward declarations**: scan for all `FnDef` nodes before emitting bodies. This enables mutual recursion.
|
||||
|
||||
### Step 4: Compile the El Compiler
|
||||
|
||||
Using your minimal implementation, compile `elc-cli.el` (which imports the entire compiler chain):
|
||||
|
||||
```bash
|
||||
# Your minimal compiler
|
||||
python3 minimal_elc.py elc-cli.el > elc-new.c
|
||||
|
||||
# Build with the runtime
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o elc-new elc-new.c el-compiler/runtime/el_runtime.c
|
||||
```
|
||||
|
||||
### Step 5: Verify Self-Hosting
|
||||
|
||||
```bash
|
||||
# Compile elc-cli.el with the new compiler
|
||||
./elc-new elc-cli.el elc-v2.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o elc-v2 elc-v2.c el-compiler/runtime/el_runtime.c
|
||||
|
||||
# Compile again with the second-generation compiler
|
||||
./elc-v2 elc-cli.el elc-v3.c
|
||||
|
||||
# The outputs should be identical
|
||||
diff elc-v2.c elc-v3.c
|
||||
```
|
||||
|
||||
A clean diff confirms you have a stable fixed point: the compiler reproduces itself exactly.
|
||||
|
||||
### Step 6: Replace the Bootstrap Binary
|
||||
|
||||
```bash
|
||||
cp elc-v2 dist/platform/elc
|
||||
```
|
||||
|
||||
You are bootstrapped.
|
||||
|
||||
### Minimal El Subset for the Compiler Itself
|
||||
|
||||
The El compiler source (`lexer.el`, `parser.el`, `codegen.el`, `compiler.el`) uses:
|
||||
- `fn`, `let`, `while`, `if`/`else`, `return`, `for`/`in`, `import`
|
||||
- `extern fn` (for `.elh` headers)
|
||||
- `String`, `Int`, `Bool`, `Void`, `Any`, `Map<String, Any>`, `[String]`, `[Map<String, Any>]`
|
||||
- Map literals `{ "key": val }`
|
||||
- Array literals `[...]` (and `native_list_empty()`)
|
||||
- List operations: `native_list_empty()`, `native_list_append()`, `native_list_get()`, `native_list_len()`, `native_list_clone()`
|
||||
- String operations: `str_join()`, `str_eq()`, `str_contains()`, `str_starts_with()`, `str_slice()`, `str_trim()`, `str_split()`, `str_index_of()`, `str_len()`, `str_to_int()`, `native_string_chars()`, `native_int_to_str()`
|
||||
- `state_get()`, `state_set()`
|
||||
- `println()`, `fs_read()`, `fs_write()`, `exit()`
|
||||
- `el_release()` (ARC cleanup)
|
||||
|
||||
The compiler does not use: HTTP, engram, dharma, LLM, crypto, UUID, float arithmetic.
|
||||
|
||||
---
|
||||
|
||||
## 5. The Long-Term Solution: elvm
|
||||
|
||||
### Why a VM Makes Bootstrapping More Auditable
|
||||
|
||||
The current bootstrap chain relies on trusting a binary whose source we cannot fully audit by inspection alone. This is the classic "trusting trust" problem (Ken Thompson, 1984). A virtual machine breaks the chain:
|
||||
|
||||
- `elc` targets `elvm` bytecode (instead of C)
|
||||
- `elvm` is a minimal interpreter hand-written in ~500 lines of C
|
||||
- The hand-written C is small enough to audit completely
|
||||
- Anyone can compile `elvm.c` with any C compiler
|
||||
- From there: `elvm` interprets `elc.elvm` → `elc` compiles El → `cc` builds native binaries
|
||||
|
||||
The benefit: the trusted base shrinks from "a Mach-O binary" to "500 lines of straightforward C code that anyone can read in an afternoon."
|
||||
|
||||
### The elvm Design
|
||||
|
||||
A minimal elvm needs:
|
||||
- A stack or register machine (stack is simpler)
|
||||
- Instructions: push, pop, add, sub, mul, div, cmp, jump, call, return, load, store
|
||||
- A string table (El strings are mostly literals)
|
||||
- A heap for ElList and ElMap
|
||||
- An FFI table mapping El runtime builtins to C functions
|
||||
|
||||
The El compiler would gain a `--target=elvm` flag in `compile_dispatch()`. Codegen would emit bytecode instead of C text. The runtime interface stays the same — builtins map to FFI slots by name.
|
||||
|
||||
This is the planned path. It does not exist yet.
|
||||
|
||||
---
|
||||
|
||||
## 6. Compiler Source Map
|
||||
|
||||
| File | Role | Lines |
|
||||
|------|------|-------|
|
||||
| `elc-cli.el` | Entry point; imports compiler.el | 7 |
|
||||
| `el-compiler/src/compiler.el` | Pipeline wiring: lex → parse → codegen. Import resolution, `--emit-header`, `fn main()`. Defines `compile()`, `compile_js()`, `compile_dispatch()`, `resolve_imports()` | 298 |
|
||||
| `el-compiler/src/lexer.el` | Tokenizer. `lex(source)` → token list. Char helpers, keyword lookup, scan_digits, scan_ident, scan_string, strip_code_comments | 747 |
|
||||
| `el-compiler/src/parser.el` | Recursive descent parser. `parse(tokens)` → AST. All statement and expression forms | 1071 |
|
||||
| `el-compiler/src/codegen.el` | C code emitter. `codegen(stmts, source)` → (streams to stdout). Expression codegen, statement codegen, function codegen, type tracking, capability enforcement, temporal type dispatch | 2721 |
|
||||
| `el-compiler/src/codegen-js.el` | JavaScript backend. `codegen_js(stmts, source)` → JS source | ~500 |
|
||||
| `el-compiler/runtime/el_runtime.h` | Full runtime API declaration | 755 |
|
||||
| `el-compiler/runtime/el_runtime.c` | Full runtime implementation | large |
|
||||
| `el-compiler/runtime/el_runtime.js` | JS runtime | — |
|
||||
| `elb.el` | Build coordinator. Reads `manifest.el`, walks import graph, compiles modules, links binary. The `.NET`-style incremental build model | 367 |
|
||||
| `elc-combined.el` | Pre-merged single-file bootstrap edition (for early bootstrap iterations) | large |
|
||||
| `spec/language.md` | Language specification v1.2.0 | — |
|
||||
| `dist/platform/elc` | Current bootstrap binary (Mach-O arm64) | — |
|
||||
|
||||
---
|
||||
|
||||
## 7. Key Decisions and Gotchas
|
||||
|
||||
### `target` is a Reserved Keyword
|
||||
|
||||
`target` is lexed as the `Target` token kind. It cannot be used as a variable or parameter name anywhere in El source. If you write `fn compile(target: String)`, the parameter name will be tokenized as `Target`, which the parser does not recognize as an `Ident` in parameter position.
|
||||
|
||||
**Workaround:** use `tgt`, `dest`, `backend`, or any other name. The compiler source uses `tgt` specifically for this reason. This comes up whenever writing code that handles compilation targets.
|
||||
|
||||
### `let x = x + 1` is Let-Rebinding, Not Mutation
|
||||
|
||||
El has no mutable variables. `let count = count + 1` re-introduces `count` into the current scope, shadowing the previous binding. At the C level, the codegen tracks declared names and emits plain assignment for subsequent bindings of the same name:
|
||||
|
||||
- First `let count = 0` → `el_val_t count = 0;`
|
||||
- Second `let count = count + 1` → `count = count + 1;`
|
||||
|
||||
This means you cannot have two different values named `count` in the same C scope — the second binding overwrites the first. This is by design. Scoped shadowing works correctly because each block (if body, while body, for body) gets its own copy of the `declared` list.
|
||||
|
||||
### Arena is Inactive in CLI Mode
|
||||
|
||||
The runtime includes an arena allocator designed for long-running server processes. In CLI mode (`elc`, `elb`) the arena is not activated. Memory is managed by ARC (reference counting via `el_retain`/`el_release`). The compiler source explicitly calls `el_release(tokens)` after parsing and `el_release(stmt)` after codegen to prevent memory exhaustion on large source files.
|
||||
|
||||
If you are implementing a new runtime or embedding El, be aware that the ARC model expects callers to release values they are done with.
|
||||
|
||||
### The `extern fn` / `.elh` Separate Compilation Model
|
||||
|
||||
`elb` (the build coordinator) supports separate compilation. When a module changes:
|
||||
1. `elc --emit-header module.el module.c` compiles the module and writes `module.elh`
|
||||
2. `module.elh` contains `extern fn` declarations for all public functions
|
||||
3. Other modules that import `module.el` use the `.elh` header instead of re-parsing the source
|
||||
|
||||
The `resolve_imports` function in `compiler.el` checks for a `.elh` file before recursively inlining the `.el` source. If the header exists, it is used (and the `.el` is marked as seen to prevent double-inclusion).
|
||||
|
||||
This is important for bootstrap: if you have pre-compiled headers lying around from a broken build, they may shadow updated source. Delete `.elh` files (or use `elb --clean`) when debugging unexpected compilation behavior.
|
||||
|
||||
### Import Resolution: Depth-First with Deduplication
|
||||
|
||||
`resolve_imports` in `compiler.el`:
|
||||
|
||||
1. Walks imports depth-first (dependencies before dependents)
|
||||
2. Uses `state_set("__elc_imp__:" + path, "1")` to deduplicate: each file is included exactly once
|
||||
3. Builds the combined source string by concatenating import bodies ahead of the entry file's body
|
||||
4. If a `.elh` header exists for an import, uses that instead of recursing into the `.el`
|
||||
|
||||
The result is one large string that gets passed through `lex` → `parse` → `codegen` as a single unit. The codegen emits forward declarations for all functions before any body, so declaration order within the combined source does not matter.
|
||||
|
||||
### `+` Operator Dispatch is Heuristic
|
||||
|
||||
El's `+` operator serves double duty: integer addition and string concatenation. The codegen dispatches based on static analysis of the AST:
|
||||
|
||||
- If either operand is a `Str` literal → `el_str_concat`
|
||||
- If both operands are provably `Int` (via `is_int_expr`) → `(a + b)`
|
||||
- If either operand is a `Call` or `Ident` → `el_str_concat` (conservative fallback)
|
||||
|
||||
The `is_int_expr` predicate recurses through the AST: literal `Int`, names in `__int_names` (from `: Int` annotations), known Int-returning builtins, and arithmetic BinOps over Int operands all count as "provably Int."
|
||||
|
||||
If you write `let result = some_int_var + 1` and `some_int_var` is not annotated `: Int`, the codegen may emit `el_str_concat` instead of integer addition. Fix by adding `: Int` to the variable declaration.
|
||||
|
||||
### `==` Operator Dispatch is Also Heuristic
|
||||
|
||||
Similarly, `==` dispatches between `str_eq(a, b)` (string comparison) and `(a == b)` (integer comparison) based on operand types. The codegen tracks Int-typed names in `__int_names`. Two `Ident` operands where both are known Int-typed use `==`; all other Ident-Ident comparisons use `str_eq`.
|
||||
|
||||
This means comparing two integer variables that were not annotated `: Int` can silently produce `str_eq` on what are actually integer values — and `str_eq` treats them as `const char*` pointers, producing incorrect results or segfaults.
|
||||
|
||||
**Rule:** always annotate variables `: Int` when they will participate in `==` comparisons or `+` arithmetic.
|
||||
|
||||
### Capability Kind Enforcement
|
||||
|
||||
The codegen classifies programs into three capability tiers based on top-level declarations:
|
||||
- `cgi` block present → full capability (all primitives allowed)
|
||||
- `service` block present → restricted (no `llm_call_agentic`, `llm_register_tool`, `dharma_emit`, `dharma_field`)
|
||||
- Neither → `utility` (no DHARMA, no LLM)
|
||||
|
||||
Violations are collected during codegen and emitted as `#error` directives at the bottom of the generated C. The downstream `cc` step then fails with a clear message naming the forbidden call.
|
||||
|
||||
### The `__no_block_expr` Parse Guard
|
||||
|
||||
When parsing the condition of `if`, `while`, `for`, and `match`, the parser sets `state_set("__no_block_expr", "1")`. This prevents `parse_primary` from treating a `{` as the start of a Map literal — instead it returns `{ "expr": "Nil" }` and the caller sees the `{` and treats it as the block delimiter.
|
||||
|
||||
Without this guard, `if a || b { ... }` would recurse into `parse_expr` for `b`, hit `{`, try to parse it as a Map literal, fail to find string keys, loop in error-recovery mode, and hang.
|
||||
|
||||
### Codegen Streams Output via `println`
|
||||
|
||||
The codegen does not build the output as a string — it calls `println()` for each line as it is emitted. The `compile()` / `compile_js()` / `codegen()` functions return `""`. Output goes to stdout.
|
||||
|
||||
This design avoids O(n²) string concatenation for large programs. It also means you cannot capture the compiler's output in a variable within El itself — you must redirect stdout at the OS level (`elc source.el > output.c`).
|
||||
|
||||
When writing to a file, `elc` detects the output path argument, redirects C's `stdout` to the file (via `freopen` in the runtime), and the `println` calls go there instead.
|
||||
Vendored
+4793
File diff suppressed because it is too large
Load Diff
Vendored
+4773
File diff suppressed because it is too large
Load Diff
BIN
Binary file not shown.
Vendored
BIN
Binary file not shown.
BIN
Binary file not shown.
+20
@@ -0,0 +1,20 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
|
||||
<plist version="1.0">
|
||||
<dict>
|
||||
<key>CFBundleDevelopmentRegion</key>
|
||||
<string>English</string>
|
||||
<key>CFBundleIdentifier</key>
|
||||
<string>com.apple.xcode.dsym.elc-asan</string>
|
||||
<key>CFBundleInfoDictionaryVersion</key>
|
||||
<string>6.0</string>
|
||||
<key>CFBundlePackageType</key>
|
||||
<string>dSYM</string>
|
||||
<key>CFBundleSignature</key>
|
||||
<string>????</string>
|
||||
<key>CFBundleShortVersionString</key>
|
||||
<string>1.0</string>
|
||||
<key>CFBundleVersion</key>
|
||||
<string>1</string>
|
||||
</dict>
|
||||
</plist>
|
||||
Binary file not shown.
+5
@@ -0,0 +1,5 @@
|
||||
---
|
||||
triple: 'arm64-apple-darwin'
|
||||
binary-path: '/Users/will/Development/neuron-technologies/foundation/el/dist/platform/elc-asan'
|
||||
relocations: []
|
||||
...
|
||||
BIN
Binary file not shown.
BIN
Binary file not shown.
Vendored
+1699
-74
File diff suppressed because it is too large
Load Diff
BIN
Binary file not shown.
BIN
Binary file not shown.
BIN
Binary file not shown.
BIN
Binary file not shown.
@@ -1469,22 +1469,25 @@ void http_serve(el_val_t port, el_val_t handler) {
|
||||
}
|
||||
int p = (int)port;
|
||||
if (p <= 0 || p > 65535) { fprintf(stderr, "http_serve: invalid port %d\n", p); return; }
|
||||
int sock = socket(AF_INET, SOCK_STREAM, 0);
|
||||
/* Dual-stack: AF_INET6 with IPV6_V6ONLY=0 accepts both IPv4 and IPv6.
|
||||
* This makes `localhost` work in browsers that resolve it to ::1 first. */
|
||||
int sock = socket(AF_INET6, SOCK_STREAM, 0);
|
||||
if (sock < 0) { perror("socket"); return; }
|
||||
int yes = 1;
|
||||
int yes = 1; int no = 0;
|
||||
setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes));
|
||||
struct sockaddr_in addr;
|
||||
setsockopt(sock, IPPROTO_IPV6, IPV6_V6ONLY, &no, sizeof(no));
|
||||
struct sockaddr_in6 addr;
|
||||
memset(&addr, 0, sizeof(addr));
|
||||
addr.sin_family = AF_INET;
|
||||
addr.sin_addr.s_addr = htonl(INADDR_ANY);
|
||||
addr.sin_port = htons((uint16_t)p);
|
||||
addr.sin6_family = AF_INET6;
|
||||
addr.sin6_addr = in6addr_any;
|
||||
addr.sin6_port = htons((uint16_t)p);
|
||||
if (bind(sock, (struct sockaddr*)&addr, sizeof(addr)) < 0) {
|
||||
perror("bind"); close(sock); return;
|
||||
}
|
||||
if (listen(sock, 64) < 0) { perror("listen"); close(sock); return; }
|
||||
fprintf(stderr, "[http] listening on 0.0.0.0:%d\n", p);
|
||||
fprintf(stderr, "[http] listening on [::]:%d (dual-stack)\n", p);
|
||||
while (1) {
|
||||
struct sockaddr_in cli;
|
||||
struct sockaddr_in6 cli;
|
||||
socklen_t clen = sizeof(cli);
|
||||
int cfd = accept(sock, (struct sockaddr*)&cli, &clen);
|
||||
if (cfd < 0) {
|
||||
@@ -1715,22 +1718,24 @@ void http_serve_v2(el_val_t port, el_val_t handler) {
|
||||
fprintf(stderr, "http_serve_v2: invalid port %d\n", p);
|
||||
return;
|
||||
}
|
||||
int sock = socket(AF_INET, SOCK_STREAM, 0);
|
||||
/* Dual-stack: same as http_serve - AF_INET6 + IPV6_V6ONLY=0. */
|
||||
int sock = socket(AF_INET6, SOCK_STREAM, 0);
|
||||
if (sock < 0) { perror("socket"); return; }
|
||||
int yes = 1;
|
||||
int yes = 1; int no = 0;
|
||||
setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes));
|
||||
struct sockaddr_in addr;
|
||||
setsockopt(sock, IPPROTO_IPV6, IPV6_V6ONLY, &no, sizeof(no));
|
||||
struct sockaddr_in6 addr;
|
||||
memset(&addr, 0, sizeof(addr));
|
||||
addr.sin_family = AF_INET;
|
||||
addr.sin_addr.s_addr = htonl(INADDR_ANY);
|
||||
addr.sin_port = htons((uint16_t)p);
|
||||
addr.sin6_family = AF_INET6;
|
||||
addr.sin6_addr = in6addr_any;
|
||||
addr.sin6_port = htons((uint16_t)p);
|
||||
if (bind(sock, (struct sockaddr*)&addr, sizeof(addr)) < 0) {
|
||||
perror("bind"); close(sock); return;
|
||||
}
|
||||
if (listen(sock, 64) < 0) { perror("listen"); close(sock); return; }
|
||||
fprintf(stderr, "[http v2] listening on 0.0.0.0:%d\n", p);
|
||||
fprintf(stderr, "[http v2] listening on [::]:%d (dual-stack)\n", p);
|
||||
while (1) {
|
||||
struct sockaddr_in cli;
|
||||
struct sockaddr_in6 cli;
|
||||
socklen_t clen = sizeof(cli);
|
||||
int cfd = accept(sock, (struct sockaddr*)&cli, &clen);
|
||||
if (cfd < 0) {
|
||||
@@ -1848,6 +1853,29 @@ el_val_t fs_write_bytes(el_val_t pathv, el_val_t bytesv, el_val_t lengthv) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
// exec_command — run a shell command, return exit code (0 = success).
|
||||
// Used by elb and other El tooling to invoke subprocesses.
|
||||
el_val_t exec_command(el_val_t cmdv) {
|
||||
const char* cmd = EL_CSTR(cmdv);
|
||||
if (!cmd) return (el_val_t)(int64_t)-1;
|
||||
int ret = system(cmd);
|
||||
return (el_val_t)(int64_t)ret;
|
||||
}
|
||||
|
||||
// exec_capture — run a shell command, capture stdout, return as String.
|
||||
// Returns "" on failure.
|
||||
el_val_t exec_capture(el_val_t cmdv) {
|
||||
const char* cmd = EL_CSTR(cmdv);
|
||||
if (!cmd) return el_wrap_str(el_strdup(""));
|
||||
FILE* f = popen(cmd, "r");
|
||||
if (!f) return el_wrap_str(el_strdup(""));
|
||||
JsonBuf b; jb_init(&b);
|
||||
char buf[4096];
|
||||
while (fgets(buf, sizeof(buf), f)) jb_puts(&b, buf);
|
||||
pclose(f);
|
||||
return el_wrap_str(b.buf);
|
||||
}
|
||||
|
||||
el_val_t fs_list(el_val_t pathv) {
|
||||
const char* path = EL_CSTR(pathv);
|
||||
el_val_t lst = el_list_empty();
|
||||
@@ -2911,8 +2939,13 @@ static int looks_like_string(el_val_t v) {
|
||||
const unsigned char* s = (const unsigned char*)p;
|
||||
for (int i = 0; i < 16; i++) {
|
||||
unsigned char c = s[i];
|
||||
if (c == '\0') return i > 0; /* terminated string */
|
||||
if (c < 0x09 || (c > 0x0d && c < 0x20) || c >= 0x7f) return 0;
|
||||
if (c == '\0') return 1; /* terminated string (empty string is still a valid string) */
|
||||
/* Reject C0 control chars (non-whitespace), allow UTF-8 high bytes.
|
||||
* 0x09-0x0d = tab/newline/cr/vt/ff (whitespace, OK)
|
||||
* 0x20-0x7e = printable ASCII (OK)
|
||||
* 0x7f = DEL (reject)
|
||||
* 0x80-0xff = UTF-8 continuation/lead bytes (OK for multi-byte chars) */
|
||||
if (c < 0x09 || (c > 0x0d && c < 0x20) || c == 0x7f) return 0;
|
||||
}
|
||||
return 1; /* 16+ printable bytes — call it a string */
|
||||
}
|
||||
@@ -3094,6 +3127,9 @@ el_val_t json_get_raw(el_val_t json_str, el_val_t key) {
|
||||
const char* json = EL_CSTR(json_str);
|
||||
const char* k = EL_CSTR(key);
|
||||
const char* p = json_find_key(json, k);
|
||||
/* Clear fs_read binary-length hint — result is a fresh null-terminated
|
||||
* string, not the raw file bytes, so Content-Length must use strlen. */
|
||||
_tl_fs_read_len = 0;
|
||||
if (!p) return el_wrap_str(el_strdup(""));
|
||||
const char* end = json_skip_value(p);
|
||||
size_t n = (size_t)(end - p);
|
||||
|
||||
@@ -739,6 +739,10 @@ el_val_t map_set(el_val_t map, el_val_t key, el_val_t value); /* el_map_set */
|
||||
/* See bottom of el_runtime.c for the implementation.
|
||||
* Configured by env vars OTLP_ENDPOINT, OTEL_SERVICE_NAME, OTEL_SERVICE_VERSION.
|
||||
* No-op when OTLP_ENDPOINT is unset. Drop-on-failure semantics. */
|
||||
/* ── Subprocess execution ────────────────────────────────────────────────── */
|
||||
el_val_t exec_command(el_val_t cmd); /* run shell command, return exit code */
|
||||
el_val_t exec_capture(el_val_t cmd); /* run shell command, capture stdout */
|
||||
|
||||
el_val_t emit_log(el_val_t level, el_val_t msg, el_val_t fields_json);
|
||||
el_val_t emit_metric(el_val_t name, el_val_t value, el_val_t tags_json);
|
||||
el_val_t trace_span_start(el_val_t name);
|
||||
|
||||
@@ -0,0 +1,679 @@
|
||||
/*
|
||||
* el_runtime.js — El language JS runtime.
|
||||
*
|
||||
* The browser/Node analog of el_runtime.c. Compiled-from-El JS source
|
||||
* imports this file once; it side-effects globalThis.__el with every
|
||||
* builtin, so generated programs can destructure the names they need
|
||||
* (see codegen-js.el's preamble).
|
||||
*
|
||||
* Value model:
|
||||
* El's tagged el_val_t collapses into JS native types here:
|
||||
* String -> string
|
||||
* Int -> number (caveat: only 53 bits of integer precision)
|
||||
* Float -> number (already a double)
|
||||
* Bool -> boolean
|
||||
* [T] -> Array
|
||||
* Map<,> -> plain object
|
||||
* Void -> undefined
|
||||
* null -> null
|
||||
*
|
||||
* Runtime mode auto-detection:
|
||||
* typeof window === 'undefined' -> Node mode
|
||||
* otherwise -> Browser mode
|
||||
*
|
||||
* See spec/codegen-js.md for the full design rationale.
|
||||
*/
|
||||
|
||||
const IS_NODE = typeof window === 'undefined' && typeof process !== 'undefined' && process.versions != null && process.versions.node != null;
|
||||
|
||||
// ── I/O ─────────────────────────────────────────────────────────────────────
|
||||
|
||||
function println(s) {
|
||||
if (IS_NODE) {
|
||||
process.stdout.write(String(s) + '\n');
|
||||
} else {
|
||||
console.log(String(s));
|
||||
}
|
||||
}
|
||||
|
||||
function print(s) {
|
||||
if (IS_NODE) {
|
||||
process.stdout.write(String(s));
|
||||
} else {
|
||||
// Browser has no stdout — fall back to console with no newline group
|
||||
console.log(String(s));
|
||||
}
|
||||
}
|
||||
|
||||
// ── String builtins ─────────────────────────────────────────────────────────
|
||||
|
||||
// Coerce both args to string and concat. Mirrors el_str_concat in C;
|
||||
// the C version handles both string-and-string and string-and-int.
|
||||
function el_str_concat(a, b) {
|
||||
return String(a) + String(b);
|
||||
}
|
||||
|
||||
function str_concat(a, b) { return el_str_concat(a, b); }
|
||||
|
||||
// Strict equality with string coercion. Matches str_eq() in C — which
|
||||
// strcmp's the underlying char*. Here we just === after coercion.
|
||||
function str_eq(a, b) {
|
||||
if (a === null || b === null) return a === b;
|
||||
return String(a) === String(b);
|
||||
}
|
||||
|
||||
function str_starts_with(s, prefix) {
|
||||
return String(s).startsWith(String(prefix));
|
||||
}
|
||||
|
||||
function str_ends_with(s, suffix) {
|
||||
return String(s).endsWith(String(suffix));
|
||||
}
|
||||
|
||||
function str_len(s) {
|
||||
return String(s).length;
|
||||
}
|
||||
|
||||
function int_to_str(n) {
|
||||
return String(n);
|
||||
}
|
||||
|
||||
function str_to_int(s) {
|
||||
const n = parseInt(String(s), 10);
|
||||
return Number.isNaN(n) ? 0 : n;
|
||||
}
|
||||
|
||||
function str_slice(s, start, end) {
|
||||
return String(s).slice(start, end);
|
||||
}
|
||||
|
||||
function str_contains(s, sub) {
|
||||
return String(s).indexOf(String(sub)) >= 0;
|
||||
}
|
||||
|
||||
function str_replace(s, from, to) {
|
||||
// Replace ALL occurrences (matches C runtime semantics).
|
||||
return String(s).split(String(from)).join(String(to));
|
||||
}
|
||||
|
||||
function str_to_upper(s) { return String(s).toUpperCase(); }
|
||||
function str_to_lower(s) { return String(s).toLowerCase(); }
|
||||
function str_upper(s) { return String(s).toUpperCase(); }
|
||||
function str_lower(s) { return String(s).toLowerCase(); }
|
||||
|
||||
function str_trim(s) { return String(s).trim(); }
|
||||
|
||||
function str_index_of(s, sub) {
|
||||
return String(s).indexOf(String(sub));
|
||||
}
|
||||
|
||||
function str_split(s, sep) {
|
||||
return String(s).split(String(sep));
|
||||
}
|
||||
|
||||
function str_char_at(s, i) {
|
||||
return String(s).charAt(i);
|
||||
}
|
||||
|
||||
function str_char_code(s, i) {
|
||||
const c = String(s).charCodeAt(i);
|
||||
return Number.isNaN(c) ? 0 : c;
|
||||
}
|
||||
|
||||
function str_pad_left(s, width, pad) {
|
||||
return String(s).padStart(width, String(pad));
|
||||
}
|
||||
|
||||
function str_pad_right(s, width, pad) {
|
||||
return String(s).padEnd(width, String(pad));
|
||||
}
|
||||
|
||||
// ── Math ────────────────────────────────────────────────────────────────────
|
||||
|
||||
function el_abs(n) { return Math.abs(n); }
|
||||
function el_max(a, b) { return a > b ? a : b; }
|
||||
function el_min(a, b) { return a < b ? a : b; }
|
||||
|
||||
// ── Refcount (no-op — JS has GC) ────────────────────────────────────────────
|
||||
|
||||
function el_retain(_v) { /* no-op */ }
|
||||
function el_release(_v) { /* no-op */ }
|
||||
|
||||
// ── List ────────────────────────────────────────────────────────────────────
|
||||
|
||||
// Variadic constructor matching el_list_new(count, items...). Exposed so
|
||||
// codegen-js can emit the same call shape if we ever want it (currently
|
||||
// codegen-js emits JS array literals directly).
|
||||
function el_list_new(_count, ...items) {
|
||||
return items.slice(0);
|
||||
}
|
||||
|
||||
function el_list_empty() { return []; }
|
||||
function el_list_clone(list) { return Array.isArray(list) ? list.slice() : []; }
|
||||
function el_list_len(list) { return Array.isArray(list) ? list.length : 0; }
|
||||
|
||||
function el_list_get(list, index) {
|
||||
if (!Array.isArray(list)) return null;
|
||||
if (index < 0 || index >= list.length) return null;
|
||||
return list[index];
|
||||
}
|
||||
|
||||
function el_list_append(list, elem) {
|
||||
if (!Array.isArray(list)) return [elem];
|
||||
const out = list.slice();
|
||||
out.push(elem);
|
||||
return out;
|
||||
}
|
||||
|
||||
function list_push(list, elem) { return el_list_append(list, elem); }
|
||||
|
||||
function list_push_front(list, elem) {
|
||||
if (!Array.isArray(list)) return [elem];
|
||||
return [elem, ...list];
|
||||
}
|
||||
|
||||
function list_join(list, sep) {
|
||||
if (!Array.isArray(list)) return '';
|
||||
return list.map(String).join(String(sep));
|
||||
}
|
||||
|
||||
function list_range(start, end) {
|
||||
const out = [];
|
||||
for (let i = start; i < end; i++) out.push(i);
|
||||
return out;
|
||||
}
|
||||
|
||||
// ── Map ─────────────────────────────────────────────────────────────────────
|
||||
|
||||
// Variadic constructor (key, val, key, val, ...).
|
||||
function el_map_new(_pairCount, ...kvs) {
|
||||
const out = {};
|
||||
for (let i = 0; i < kvs.length; i += 2) {
|
||||
out[String(kvs[i])] = kvs[i + 1];
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
function el_get_field(map, key) {
|
||||
if (map === null || map === undefined) return null;
|
||||
if (typeof map !== 'object') return null;
|
||||
const k = String(key);
|
||||
if (Object.prototype.hasOwnProperty.call(map, k)) return map[k];
|
||||
return null;
|
||||
}
|
||||
|
||||
function el_map_get(map, key) { return el_get_field(map, key); }
|
||||
|
||||
function el_map_set(map, key, value) {
|
||||
// Match the C runtime: shallow-copy + set, persistent semantics.
|
||||
const out = (map && typeof map === 'object') ? { ...map } : {};
|
||||
out[String(key)] = value;
|
||||
return out;
|
||||
}
|
||||
|
||||
// ── Method-call shorthand aliases ──────────────────────────────────────────
|
||||
// `obj.method(args)` compiles to `method(obj, args)` per El convention.
|
||||
|
||||
function append(list, elem) { return el_list_append(list, elem); }
|
||||
function len(v) {
|
||||
if (Array.isArray(v)) return v.length;
|
||||
if (typeof v === 'string') return v.length;
|
||||
if (v && typeof v === 'object') return Object.keys(v).length;
|
||||
return 0;
|
||||
}
|
||||
function get(list, index) { return el_list_get(list, index); }
|
||||
function map_get(m, k) { return el_get_field(m, k); }
|
||||
function map_set(m, k, v) { return el_map_set(m, k, v); }
|
||||
|
||||
// ── Native VM aliases ──────────────────────────────────────────────────────
|
||||
|
||||
function native_list_get(list, index) { return el_list_get(list, index); }
|
||||
function native_list_len(list) { return el_list_len(list); }
|
||||
function native_list_append(list, elem) { return el_list_append(list, elem); }
|
||||
function native_list_empty() { return []; }
|
||||
function native_list_clone(list) { return el_list_clone(list); }
|
||||
function native_string_chars(s) { return String(s).split(''); }
|
||||
function native_int_to_str(n) { return String(n); }
|
||||
|
||||
// ── HTTP ───────────────────────────────────────────────────────────────────
|
||||
//
|
||||
// fetch() is async. These return Promise<string>. Generated El code does
|
||||
// not yet emit await — that's the async-taint pass (see spec §5). For
|
||||
// programs that don't touch HTTP this is fine; for programs that do,
|
||||
// the value will appear as "[object Promise]" until the taint pass lands.
|
||||
|
||||
function http_get(url) {
|
||||
if (typeof fetch === 'undefined') {
|
||||
throw new Error('http_get: fetch() not available in this runtime');
|
||||
}
|
||||
return fetch(String(url)).then(r => r.text());
|
||||
}
|
||||
|
||||
function http_post(url, body) {
|
||||
if (typeof fetch === 'undefined') {
|
||||
throw new Error('http_post: fetch() not available in this runtime');
|
||||
}
|
||||
return fetch(String(url), { method: 'POST', body: String(body) }).then(r => r.text());
|
||||
}
|
||||
|
||||
function http_post_json(url, jsonBody) {
|
||||
if (typeof fetch === 'undefined') {
|
||||
throw new Error('http_post_json: fetch() not available in this runtime');
|
||||
}
|
||||
return fetch(String(url), {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: String(jsonBody),
|
||||
}).then(r => r.text());
|
||||
}
|
||||
|
||||
function http_get_with_headers(url, headersMap) {
|
||||
if (typeof fetch === 'undefined') {
|
||||
throw new Error('http_get_with_headers: fetch() not available');
|
||||
}
|
||||
return fetch(String(url), { headers: headersMap || {} }).then(r => r.text());
|
||||
}
|
||||
|
||||
function http_post_with_headers(url, body, headersMap) {
|
||||
if (typeof fetch === 'undefined') {
|
||||
throw new Error('http_post_with_headers: fetch() not available');
|
||||
}
|
||||
return fetch(String(url), {
|
||||
method: 'POST',
|
||||
headers: headersMap || {},
|
||||
body: String(body),
|
||||
}).then(r => r.text());
|
||||
}
|
||||
|
||||
function http_serve(_port, _handler) {
|
||||
throw new Error('http_serve: not supported in JS target — needs server-side runtime mode');
|
||||
}
|
||||
|
||||
function http_set_handler(_name) {
|
||||
throw new Error('http_set_handler: not supported in JS target');
|
||||
}
|
||||
|
||||
// ── Filesystem (Node-only) ─────────────────────────────────────────────────
|
||||
|
||||
function _ensureNode(name) {
|
||||
if (!IS_NODE) {
|
||||
throw new Error(`${name}: not supported in browser runtime`);
|
||||
}
|
||||
}
|
||||
|
||||
function fs_read(path) {
|
||||
_ensureNode('fs_read');
|
||||
const fs = require('node:fs');
|
||||
try {
|
||||
return fs.readFileSync(String(path), 'utf8');
|
||||
} catch (_e) {
|
||||
return '';
|
||||
}
|
||||
}
|
||||
|
||||
function fs_write(path, content) {
|
||||
_ensureNode('fs_write');
|
||||
const fs = require('node:fs');
|
||||
try {
|
||||
fs.writeFileSync(String(path), String(content));
|
||||
return true;
|
||||
} catch (_e) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
function fs_list(path) {
|
||||
_ensureNode('fs_list');
|
||||
const fs = require('node:fs');
|
||||
try {
|
||||
return fs.readdirSync(String(path));
|
||||
} catch (_e) {
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
// ── JSON ───────────────────────────────────────────────────────────────────
|
||||
|
||||
function json_parse(s) {
|
||||
try { return JSON.parse(String(s)); }
|
||||
catch (_e) { return null; }
|
||||
}
|
||||
|
||||
function json_stringify(v) {
|
||||
try { return JSON.stringify(v); }
|
||||
catch (_e) { return ''; }
|
||||
}
|
||||
|
||||
function json_get(jsonStr, key) {
|
||||
const o = json_parse(jsonStr);
|
||||
if (o === null) return null;
|
||||
return el_get_field(o, key);
|
||||
}
|
||||
|
||||
function json_get_string(jsonStr, key) {
|
||||
const v = json_get(jsonStr, key);
|
||||
return v === null ? '' : String(v);
|
||||
}
|
||||
|
||||
function json_get_int(jsonStr, key) {
|
||||
const v = json_get(jsonStr, key);
|
||||
if (typeof v === 'number') return Math.trunc(v);
|
||||
if (typeof v === 'string') return str_to_int(v);
|
||||
return 0;
|
||||
}
|
||||
|
||||
function json_get_float(jsonStr, key) {
|
||||
const v = json_get(jsonStr, key);
|
||||
return typeof v === 'number' ? v : 0;
|
||||
}
|
||||
|
||||
function json_get_bool(jsonStr, key) {
|
||||
const v = json_get(jsonStr, key);
|
||||
return v === true;
|
||||
}
|
||||
|
||||
function json_get_raw(jsonStr, key) {
|
||||
const v = json_get(jsonStr, key);
|
||||
return v === null ? '' : json_stringify(v);
|
||||
}
|
||||
|
||||
function json_set(jsonStr, key, value) {
|
||||
const o = json_parse(jsonStr) ?? {};
|
||||
o[String(key)] = value;
|
||||
return json_stringify(o);
|
||||
}
|
||||
|
||||
function json_array_len(jsonStr) {
|
||||
const o = json_parse(jsonStr);
|
||||
return Array.isArray(o) ? o.length : 0;
|
||||
}
|
||||
|
||||
// ── Time ───────────────────────────────────────────────────────────────────
|
||||
|
||||
function time_now() {
|
||||
return Math.floor(Date.now() / 1000);
|
||||
}
|
||||
|
||||
function time_now_utc() {
|
||||
// In the C runtime this returns nanoseconds since epoch. JS number
|
||||
// can't represent that range past ~2^53. We return milliseconds — a
|
||||
// safe range — and document the divergence.
|
||||
return Date.now();
|
||||
}
|
||||
|
||||
function sleep_secs(secs) {
|
||||
if (!IS_NODE) {
|
||||
throw new Error('sleep_secs: blocking sleep not supported in browser');
|
||||
}
|
||||
// Simple sync sleep via Atomics.wait on a SharedArrayBuffer-backed Int32.
|
||||
const sab = new SharedArrayBuffer(4);
|
||||
const i32 = new Int32Array(sab);
|
||||
Atomics.wait(i32, 0, 0, Math.floor(secs * 1000));
|
||||
return secs;
|
||||
}
|
||||
|
||||
function sleep_ms(ms) {
|
||||
if (!IS_NODE) {
|
||||
throw new Error('sleep_ms: blocking sleep not supported in browser');
|
||||
}
|
||||
const sab = new SharedArrayBuffer(4);
|
||||
const i32 = new Int32Array(sab);
|
||||
Atomics.wait(i32, 0, 0, Math.floor(ms));
|
||||
return ms;
|
||||
}
|
||||
|
||||
// ── Bool ───────────────────────────────────────────────────────────────────
|
||||
|
||||
function bool_to_str(b) { return b ? 'true' : 'false'; }
|
||||
|
||||
// ── Process ────────────────────────────────────────────────────────────────
|
||||
|
||||
function exit_program(code) {
|
||||
if (IS_NODE) {
|
||||
process.exit(code | 0);
|
||||
} else {
|
||||
throw new Error(`exit_program(${code}) called in browser`);
|
||||
}
|
||||
}
|
||||
|
||||
// ── args() ─────────────────────────────────────────────────────────────────
|
||||
|
||||
function args() {
|
||||
if (IS_NODE) {
|
||||
// process.argv is [node, script, ...args] — slice off node + script.
|
||||
return process.argv.slice(2);
|
||||
}
|
||||
return [];
|
||||
}
|
||||
|
||||
// ── env ────────────────────────────────────────────────────────────────────
|
||||
|
||||
function env(key) {
|
||||
if (IS_NODE) {
|
||||
const v = process.env[String(key)];
|
||||
return v === undefined ? null : v;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
// ── In-process state K/V ───────────────────────────────────────────────────
|
||||
|
||||
const _stateMap = new Map();
|
||||
|
||||
function state_set(key, value) {
|
||||
_stateMap.set(String(key), value);
|
||||
return value;
|
||||
}
|
||||
|
||||
function state_get(key) {
|
||||
const v = _stateMap.get(String(key));
|
||||
return v === undefined ? '' : v;
|
||||
}
|
||||
|
||||
function state_del(key) {
|
||||
return _stateMap.delete(String(key));
|
||||
}
|
||||
|
||||
function state_keys() {
|
||||
return Array.from(_stateMap.keys());
|
||||
}
|
||||
|
||||
// ── UUID ───────────────────────────────────────────────────────────────────
|
||||
|
||||
function uuid_v4() {
|
||||
// RFC 4122-ish — uses crypto when available, falls back to Math.random.
|
||||
if (typeof crypto !== 'undefined' && crypto.randomUUID) {
|
||||
return crypto.randomUUID();
|
||||
}
|
||||
return 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'.replace(/[xy]/g, c => {
|
||||
const r = Math.random() * 16 | 0;
|
||||
const v = c === 'x' ? r : (r & 0x3 | 0x8);
|
||||
return v.toString(16);
|
||||
});
|
||||
}
|
||||
function uuid_new() { return uuid_v4(); }
|
||||
|
||||
// ── Float formatting ───────────────────────────────────────────────────────
|
||||
|
||||
function float_to_str(f) { return String(f); }
|
||||
function int_to_float(n) { return n; }
|
||||
function float_to_int(f) { return Math.trunc(f); }
|
||||
|
||||
function format_float(f, decimals) {
|
||||
return Number(f).toFixed(decimals);
|
||||
}
|
||||
|
||||
function decimal_round(f, decimals) {
|
||||
const m = Math.pow(10, decimals);
|
||||
return Math.round(f * m) / m;
|
||||
}
|
||||
|
||||
function str_to_float(s) {
|
||||
const n = parseFloat(String(s));
|
||||
return Number.isNaN(n) ? 0 : n;
|
||||
}
|
||||
|
||||
// ── Math (Float-aware) ─────────────────────────────────────────────────────
|
||||
|
||||
function math_sqrt(f) { return Math.sqrt(f); }
|
||||
function math_log(f) { return Math.log10(f); }
|
||||
function math_ln(f) { return Math.log(f); }
|
||||
function math_sin(f) { return Math.sin(f); }
|
||||
function math_cos(f) { return Math.cos(f); }
|
||||
function math_pi() { return Math.PI; }
|
||||
|
||||
// ── Stubs for not-yet-supported features ───────────────────────────────────
|
||||
//
|
||||
// These compile but throw when called. See spec/codegen-js.md §7.
|
||||
|
||||
function _notSupported(name) {
|
||||
return () => { throw new Error(`${name}: not supported in JS target — needs server-side delegation`); };
|
||||
}
|
||||
|
||||
// CGI identity
|
||||
function el_cgi_init(_name, _did, _principal, _network, _engram) {
|
||||
// No-op — UI code is not a CGI principal. See spec §7.
|
||||
}
|
||||
|
||||
// DHARMA — all stubbed.
|
||||
const dharma_connect = _notSupported('dharma_connect');
|
||||
const dharma_send = _notSupported('dharma_send');
|
||||
const dharma_activate = _notSupported('dharma_activate');
|
||||
const dharma_emit = _notSupported('dharma_emit');
|
||||
const dharma_field = _notSupported('dharma_field');
|
||||
const dharma_strengthen = _notSupported('dharma_strengthen');
|
||||
const dharma_relationship = _notSupported('dharma_relationship');
|
||||
const dharma_peers = _notSupported('dharma_peers');
|
||||
|
||||
// Engram — stubbed (could be ported to in-browser later).
|
||||
const engram_node = _notSupported('engram_node');
|
||||
const engram_node_full = _notSupported('engram_node_full');
|
||||
const engram_get_node = _notSupported('engram_get_node');
|
||||
const engram_strengthen = _notSupported('engram_strengthen');
|
||||
const engram_forget = _notSupported('engram_forget');
|
||||
const engram_node_count = _notSupported('engram_node_count');
|
||||
const engram_search = _notSupported('engram_search');
|
||||
const engram_scan_nodes = _notSupported('engram_scan_nodes');
|
||||
const engram_connect = _notSupported('engram_connect');
|
||||
const engram_edge_between = _notSupported('engram_edge_between');
|
||||
const engram_neighbors = _notSupported('engram_neighbors');
|
||||
const engram_neighbors_filtered = _notSupported('engram_neighbors_filtered');
|
||||
const engram_edge_count = _notSupported('engram_edge_count');
|
||||
const engram_activate = _notSupported('engram_activate');
|
||||
const engram_save = _notSupported('engram_save');
|
||||
const engram_load = _notSupported('engram_load');
|
||||
|
||||
// LLM — stubbed (browser cannot hold API keys safely).
|
||||
const llm_call = _notSupported('llm_call');
|
||||
const llm_call_system = _notSupported('llm_call_system');
|
||||
const llm_call_agentic = _notSupported('llm_call_agentic');
|
||||
const llm_vision = _notSupported('llm_vision');
|
||||
const llm_models = _notSupported('llm_models');
|
||||
const llm_register_tool = _notSupported('llm_register_tool');
|
||||
|
||||
// Crypto — stubbed; could be backed by SubtleCrypto later.
|
||||
const sha256_hex = _notSupported('sha256_hex');
|
||||
const sha256_bytes = _notSupported('sha256_bytes');
|
||||
const hmac_sha256_hex = _notSupported('hmac_sha256_hex');
|
||||
const hmac_sha256_bytes = _notSupported('hmac_sha256_bytes');
|
||||
const base64_encode = _notSupported('base64_encode');
|
||||
const base64_decode = _notSupported('base64_decode');
|
||||
const base64url_encode = _notSupported('base64url_encode');
|
||||
const base64url_decode = _notSupported('base64url_decode');
|
||||
|
||||
// ── Export to globalThis.__el ──────────────────────────────────────────────
|
||||
//
|
||||
// Generated programs destructure off this object. Keeping it on globalThis
|
||||
// means a single `import "./el_runtime.js"` is enough; no per-call namespace
|
||||
// prefix is required at codegen time.
|
||||
|
||||
const __el = {
|
||||
// I/O
|
||||
println, print,
|
||||
// String
|
||||
el_str_concat, str_concat, str_eq, str_starts_with, str_ends_with,
|
||||
str_len, int_to_str, str_to_int, str_slice, str_contains, str_replace,
|
||||
str_to_upper, str_to_lower, str_trim, str_index_of, str_split, str_char_at,
|
||||
str_char_code, str_lower, str_upper, str_pad_left, str_pad_right,
|
||||
// Math
|
||||
el_abs, el_max, el_min,
|
||||
// Refcount
|
||||
el_retain, el_release,
|
||||
// List
|
||||
el_list_new, el_list_empty, el_list_clone, el_list_len, el_list_get,
|
||||
el_list_append, list_push, list_push_front, list_join, list_range,
|
||||
// Map
|
||||
el_map_new, el_get_field, el_map_get, el_map_set,
|
||||
// Method-call shortforms
|
||||
append, len, get, map_get, map_set,
|
||||
// Native VM aliases
|
||||
native_list_get, native_list_len, native_list_append, native_list_empty,
|
||||
native_list_clone, native_string_chars, native_int_to_str,
|
||||
// HTTP
|
||||
http_get, http_post, http_post_json, http_get_with_headers,
|
||||
http_post_with_headers, http_serve, http_set_handler,
|
||||
// FS
|
||||
fs_read, fs_write, fs_list,
|
||||
// JSON
|
||||
json_parse, json_stringify, json_get, json_get_string, json_get_int,
|
||||
json_get_float, json_get_bool, json_get_raw, json_set, json_array_len,
|
||||
// Time
|
||||
time_now, time_now_utc, sleep_secs, sleep_ms,
|
||||
// Bool
|
||||
bool_to_str,
|
||||
// Process
|
||||
exit_program,
|
||||
// Args / env
|
||||
args, env,
|
||||
// State
|
||||
state_set, state_get, state_del, state_keys,
|
||||
// UUID
|
||||
uuid_v4, uuid_new,
|
||||
// Float / math
|
||||
float_to_str, int_to_float, float_to_int, format_float, decimal_round,
|
||||
str_to_float, math_sqrt, math_log, math_ln, math_sin, math_cos, math_pi,
|
||||
// CGI / DHARMA / Engram / LLM (stubs)
|
||||
el_cgi_init,
|
||||
dharma_connect, dharma_send, dharma_activate, dharma_emit, dharma_field,
|
||||
dharma_strengthen, dharma_relationship, dharma_peers,
|
||||
engram_node, engram_node_full, engram_get_node, engram_strengthen,
|
||||
engram_forget, engram_node_count, engram_search, engram_scan_nodes,
|
||||
engram_connect, engram_edge_between, engram_neighbors,
|
||||
engram_neighbors_filtered, engram_edge_count, engram_activate,
|
||||
engram_save, engram_load,
|
||||
llm_call, llm_call_system, llm_call_agentic, llm_vision,
|
||||
llm_models, llm_register_tool,
|
||||
// Crypto (stubs)
|
||||
sha256_hex, sha256_bytes, hmac_sha256_hex, hmac_sha256_bytes,
|
||||
base64_encode, base64_decode, base64url_encode, base64url_decode,
|
||||
};
|
||||
|
||||
globalThis.__el = __el;
|
||||
|
||||
// Also re-export as ES module exports for consumers that prefer that style.
|
||||
export { __el as default };
|
||||
export {
|
||||
println, print,
|
||||
el_str_concat, str_concat, str_eq, str_starts_with, str_ends_with,
|
||||
str_len, int_to_str, str_to_int, str_slice, str_contains, str_replace,
|
||||
str_to_upper, str_to_lower, str_trim, str_index_of, str_split, str_char_at,
|
||||
str_char_code, str_lower, str_upper,
|
||||
el_abs, el_max, el_min,
|
||||
el_retain, el_release,
|
||||
el_list_new, el_list_empty, el_list_clone, el_list_len, el_list_get,
|
||||
el_list_append, list_push, list_push_front, list_join, list_range,
|
||||
el_map_new, el_get_field, el_map_get, el_map_set,
|
||||
append, len, get, map_get, map_set,
|
||||
native_list_get, native_list_len, native_list_append, native_list_empty,
|
||||
native_list_clone, native_string_chars, native_int_to_str,
|
||||
http_get, http_post, http_post_json,
|
||||
fs_read, fs_write, fs_list,
|
||||
json_parse, json_stringify, json_get, json_get_string, json_get_int,
|
||||
time_now, time_now_utc, sleep_ms,
|
||||
bool_to_str, exit_program, args, env,
|
||||
state_set, state_get, state_del, state_keys,
|
||||
el_cgi_init,
|
||||
dharma_connect, dharma_send, dharma_activate, dharma_emit, dharma_field,
|
||||
engram_node, engram_search, engram_activate,
|
||||
llm_call, llm_call_system,
|
||||
};
|
||||
@@ -0,0 +1,926 @@
|
||||
// codegen-js.el — El compiler JavaScript source code generator
|
||||
//
|
||||
// Input: list of AST statement maps (from parser.el)
|
||||
// Output: JavaScript source printed to stdout (streamed, one line at a time)
|
||||
//
|
||||
// Each El program compiles to a single .js file that imports el_runtime.js
|
||||
// (which side-effects globals so call sites stay flat — println(x), not
|
||||
// el.println(x)). Functions map to JS function declarations; top-level
|
||||
// statements run at module load.
|
||||
//
|
||||
// Entry point: fn codegen_js(stmts: [Map<String, Any>], source: String) -> String
|
||||
// Returns "" — output goes to stdout via println().
|
||||
//
|
||||
// This file mirrors codegen.el (the C backend). Where the C backend has to
|
||||
// fight the int64_t-everywhere convention to dispatch arithmetic vs concat
|
||||
// or `==` vs `str_eq`, the JS backend can usually let JS's own operator
|
||||
// semantics do the right thing. We retain the dispatch logic for clarity
|
||||
// and so that explicit calls to `el_str_concat` or `str_eq` still work.
|
||||
|
||||
// ── String helpers ────────────────────────────────────────────────────────────
|
||||
|
||||
// Escape a JS string literal (double-quotes, backslashes, newlines, etc.).
|
||||
fn js_escape(s: String) -> String {
|
||||
let chars: [String] = native_string_chars(s)
|
||||
let total: Int = native_list_len(chars)
|
||||
let parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < total {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if ch == "\"" {
|
||||
let parts = native_list_append(parts, "\\\"")
|
||||
} else {
|
||||
if ch == "\\" {
|
||||
let parts = native_list_append(parts, "\\\\")
|
||||
} else {
|
||||
if ch == "\n" {
|
||||
let parts = native_list_append(parts, "\\n")
|
||||
} else {
|
||||
if ch == "\r" {
|
||||
let parts = native_list_append(parts, "\\r")
|
||||
} else {
|
||||
if ch == "\t" {
|
||||
let parts = native_list_append(parts, "\\t")
|
||||
} else {
|
||||
let parts = native_list_append(parts, ch)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
str_join(parts, "")
|
||||
}
|
||||
|
||||
fn js_str_lit(s: String) -> String {
|
||||
"\"" + js_escape(s) + "\""
|
||||
}
|
||||
|
||||
// ── Code emission ─────────────────────────────────────────────────────────────
|
||||
|
||||
fn js_emit_line(line: String) -> Void {
|
||||
println(line)
|
||||
}
|
||||
|
||||
fn js_emit_blank() -> Void {
|
||||
println("")
|
||||
}
|
||||
|
||||
// ── Operator helpers ──────────────────────────────────────────────────────────
|
||||
|
||||
fn js_binop(op: String) -> String {
|
||||
if op == "Plus" { return "+" }
|
||||
if op == "Minus" { return "-" }
|
||||
if op == "Star" { return "*" }
|
||||
if op == "Slash" { return "/" }
|
||||
if op == "Percent" { return "%" }
|
||||
if op == "EqEq" { return "===" }
|
||||
if op == "NotEq" { return "!==" }
|
||||
if op == "Lt" { return "<" }
|
||||
if op == "Gt" { return ">" }
|
||||
if op == "LtEq" { return "<=" }
|
||||
if op == "GtEq" { return ">=" }
|
||||
if op == "And" { return "&&" }
|
||||
if op == "Or" { return "||" }
|
||||
op
|
||||
}
|
||||
|
||||
// ── Int-name tracking (mirrors codegen.el) ────────────────────────────────────
|
||||
|
||||
fn js_is_int_name(name: String) -> Bool {
|
||||
let csv: String = state_get("__js_int_names")
|
||||
if str_eq(csv, "") { return false }
|
||||
return str_contains(csv, "," + name + ",")
|
||||
}
|
||||
|
||||
fn js_add_int_name(name: String) -> Bool {
|
||||
let csv: String = state_get("__js_int_names")
|
||||
if str_eq(csv, "") { csv = "," }
|
||||
let key: String = "," + name + ","
|
||||
if str_contains(csv, key) { return true }
|
||||
state_set("__js_int_names", csv + name + ",")
|
||||
return true
|
||||
}
|
||||
|
||||
fn js_build_int_names_for_params(params: [Map<String, Any>]) -> Bool {
|
||||
state_set("__js_int_names", ",")
|
||||
let np: Int = native_list_len(params)
|
||||
let pi = 0
|
||||
while pi < np {
|
||||
let param = native_list_get(params, pi)
|
||||
let pname: String = param["name"]
|
||||
let ptype: String = param["type"]
|
||||
if str_eq(ptype, "Int") {
|
||||
js_add_int_name(pname)
|
||||
}
|
||||
let pi = pi + 1
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
fn js_is_int_call(call_expr: Map<String, Any>) -> Bool {
|
||||
let func = call_expr["func"]
|
||||
let fk: String = func["expr"]
|
||||
if !str_eq(fk, "Ident") { return false }
|
||||
let name: String = func["name"]
|
||||
if str_eq(name, "str_len") { return true }
|
||||
if str_eq(name, "str_index_of") { return true }
|
||||
if str_eq(name, "str_to_int") { return true }
|
||||
if str_eq(name, "str_char_code") { return true }
|
||||
if str_eq(name, "native_list_len") { return true }
|
||||
if str_eq(name, "el_list_len") { return true }
|
||||
if str_eq(name, "len") { return true }
|
||||
if str_eq(name, "json_get_int") { return true }
|
||||
if str_eq(name, "time_now") { return true }
|
||||
if str_eq(name, "time_now_utc") { return true }
|
||||
if str_eq(name, "el_abs") { return true }
|
||||
if str_eq(name, "el_max") { return true }
|
||||
if str_eq(name, "el_min") { return true }
|
||||
return false
|
||||
}
|
||||
|
||||
// ── Expression codegen ────────────────────────────────────────────────────────
|
||||
//
|
||||
// js_cg_expr returns a JS expression string (not a statement).
|
||||
//
|
||||
// Note: the C backend's `+` dispatch is preserved here for two reasons:
|
||||
// 1) Generated output stays grep-equivalent across targets
|
||||
// 2) Explicit `el_str_concat()` lives in the runtime; codegen routes
|
||||
// through it for ambiguous (Ident+Ident, Call+Call) cases. JS's
|
||||
// own `+` would also work, but el_str_concat coerces both sides
|
||||
// to strings — closer to the C semantics.
|
||||
|
||||
fn js_cg_expr(expr: Map<String, Any>) -> String {
|
||||
let kind: String = expr["expr"]
|
||||
|
||||
if kind == "Int" {
|
||||
let v: String = expr["value"]
|
||||
return v
|
||||
}
|
||||
|
||||
// DurationLit — postfix-literal time value (e.g. 30.seconds, 1.hour).
|
||||
// The JS backend lowers to a literal integer nanosecond count. The C
|
||||
// backend uses the typed wrapper el_duration_from_nanos to make intent
|
||||
// explicit at the runtime boundary; JS has no equivalent shim yet, so
|
||||
// we lower directly. A future Phase 2 JS time runtime can route through
|
||||
// a wrapper once added.
|
||||
if kind == "DurationLit" {
|
||||
let count: String = expr["count"]
|
||||
let unit: String = expr["unit"]
|
||||
let mult_ns = "1"
|
||||
if str_eq(unit, "nano") { let mult_ns = "1" }
|
||||
if str_eq(unit, "nanos") { let mult_ns = "1" }
|
||||
if str_eq(unit, "milli") { let mult_ns = "1000000" }
|
||||
if str_eq(unit, "millis") { let mult_ns = "1000000" }
|
||||
if str_eq(unit, "millisecond") { let mult_ns = "1000000" }
|
||||
if str_eq(unit, "milliseconds") { let mult_ns = "1000000" }
|
||||
if str_eq(unit, "second") { let mult_ns = "1000000000" }
|
||||
if str_eq(unit, "seconds") { let mult_ns = "1000000000" }
|
||||
if str_eq(unit, "minute") { let mult_ns = "60000000000" }
|
||||
if str_eq(unit, "minutes") { let mult_ns = "60000000000" }
|
||||
if str_eq(unit, "hour") { let mult_ns = "3600000000000" }
|
||||
if str_eq(unit, "hours") { let mult_ns = "3600000000000" }
|
||||
if str_eq(unit, "day") { let mult_ns = "86400000000000" }
|
||||
if str_eq(unit, "days") { let mult_ns = "86400000000000" }
|
||||
return "(" + count + " * " + mult_ns + ")"
|
||||
}
|
||||
|
||||
if kind == "Float" {
|
||||
// JS numbers are already doubles — no bit-cast trick needed.
|
||||
let v: String = expr["value"]
|
||||
return v
|
||||
}
|
||||
|
||||
if kind == "Str" {
|
||||
let v: String = expr["value"]
|
||||
return js_str_lit(v)
|
||||
}
|
||||
|
||||
if kind == "Bool" {
|
||||
let v: String = expr["value"]
|
||||
if v == "true" { return "true" }
|
||||
return "false"
|
||||
}
|
||||
|
||||
if kind == "Nil" {
|
||||
return "null"
|
||||
}
|
||||
|
||||
if kind == "Ident" {
|
||||
let name: String = expr["name"]
|
||||
return name
|
||||
}
|
||||
|
||||
if kind == "Not" {
|
||||
let inner = expr["inner"]
|
||||
let inner_c: String = js_cg_expr(inner)
|
||||
return "!" + inner_c
|
||||
}
|
||||
|
||||
if kind == "Neg" {
|
||||
let inner = expr["inner"]
|
||||
let inner_c: String = js_cg_expr(inner)
|
||||
return "(-" + inner_c + ")"
|
||||
}
|
||||
|
||||
if kind == "BinOp" {
|
||||
let op: String = expr["op"]
|
||||
let left = expr["left"]
|
||||
let right = expr["right"]
|
||||
let left_c: String = js_cg_expr(left)
|
||||
let right_c: String = js_cg_expr(right)
|
||||
let left_kind: String = left["expr"]
|
||||
let right_kind: String = right["expr"]
|
||||
|
||||
// Plus dispatch — same shape as C backend, but we route through
|
||||
// el_str_concat for the string-concat path (its JS impl coerces
|
||||
// and matches C's behavior). Arithmetic uses bare JS `+`.
|
||||
if op == "Plus" {
|
||||
if left_kind == "Str" {
|
||||
return "el_str_concat(" + left_c + ", " + right_c + ")"
|
||||
}
|
||||
if right_kind == "Str" {
|
||||
return "el_str_concat(" + left_c + ", " + right_c + ")"
|
||||
}
|
||||
if left_kind == "Int" {
|
||||
return "(" + left_c + " + " + right_c + ")"
|
||||
}
|
||||
if right_kind == "Int" {
|
||||
return "(" + left_c + " + " + right_c + ")"
|
||||
}
|
||||
if left_kind == "Ident" {
|
||||
if right_kind == "Ident" {
|
||||
let lname: String = left["name"]
|
||||
let rname: String = right["name"]
|
||||
if js_is_int_name(lname) {
|
||||
if js_is_int_name(rname) {
|
||||
return "(" + left_c + " + " + right_c + ")"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if left_kind == "Ident" {
|
||||
if right_kind == "Call" {
|
||||
let lname: String = left["name"]
|
||||
if js_is_int_name(lname) {
|
||||
if js_is_int_call(right) {
|
||||
return "(" + left_c + " + " + right_c + ")"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if right_kind == "Ident" {
|
||||
if left_kind == "Call" {
|
||||
let rname: String = right["name"]
|
||||
if js_is_int_name(rname) {
|
||||
if js_is_int_call(left) {
|
||||
return "(" + left_c + " + " + right_c + ")"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if left_kind == "Call" {
|
||||
if right_kind == "Call" {
|
||||
if js_is_int_call(left) {
|
||||
if js_is_int_call(right) {
|
||||
return "(" + left_c + " + " + right_c + ")"
|
||||
}
|
||||
}
|
||||
}
|
||||
return "el_str_concat(" + left_c + ", " + right_c + ")"
|
||||
}
|
||||
if right_kind == "Call" {
|
||||
return "el_str_concat(" + left_c + ", " + right_c + ")"
|
||||
}
|
||||
// Fallback: when in doubt, route through el_str_concat. JS's
|
||||
// own + handles strings and numbers natively, but el_str_concat
|
||||
// gives us a single point of control if behavior needs to diverge.
|
||||
if left_kind == "Ident" {
|
||||
return "el_str_concat(" + left_c + ", " + right_c + ")"
|
||||
}
|
||||
if right_kind == "Ident" {
|
||||
return "el_str_concat(" + left_c + ", " + right_c + ")"
|
||||
}
|
||||
}
|
||||
|
||||
// Equality dispatch — C backend disambiguates via str_eq for
|
||||
// strings and == for ints. JS does both with === if we know
|
||||
// the types are uniform; for ambiguous identifier pairs we
|
||||
// route through str_eq for safety (it falls back to === in JS).
|
||||
if op == "EqEq" {
|
||||
if left_kind == "Int" { return "(" + left_c + " === " + right_c + ")" }
|
||||
if right_kind == "Int" { return "(" + left_c + " === " + right_c + ")" }
|
||||
if left_kind == "Bool" { return "(" + left_c + " === " + right_c + ")" }
|
||||
if right_kind == "Bool" { return "(" + left_c + " === " + right_c + ")" }
|
||||
if left_kind == "Nil" { return "(" + left_c + " === " + right_c + ")" }
|
||||
if right_kind == "Nil" { return "(" + left_c + " === " + right_c + ")" }
|
||||
if left_kind == "Ident" {
|
||||
if right_kind == "Ident" {
|
||||
let lname: String = left["name"]
|
||||
let rname: String = right["name"]
|
||||
if js_is_int_name(lname) {
|
||||
if js_is_int_name(rname) {
|
||||
return "(" + left_c + " === " + right_c + ")"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if left_kind == "Str" { return "str_eq(" + left_c + ", " + right_c + ")" }
|
||||
if right_kind == "Str" { return "str_eq(" + left_c + ", " + right_c + ")" }
|
||||
// Default: === (works for strings, numbers, bools in JS)
|
||||
return "(" + left_c + " === " + right_c + ")"
|
||||
}
|
||||
|
||||
if op == "NotEq" {
|
||||
if left_kind == "Int" { return "(" + left_c + " !== " + right_c + ")" }
|
||||
if right_kind == "Int" { return "(" + left_c + " !== " + right_c + ")" }
|
||||
if left_kind == "Bool" { return "(" + left_c + " !== " + right_c + ")" }
|
||||
if right_kind == "Bool" { return "(" + left_c + " !== " + right_c + ")" }
|
||||
if left_kind == "Nil" { return "(" + left_c + " !== " + right_c + ")" }
|
||||
if right_kind == "Nil" { return "(" + left_c + " !== " + right_c + ")" }
|
||||
if left_kind == "Ident" {
|
||||
if right_kind == "Ident" {
|
||||
let lname: String = left["name"]
|
||||
let rname: String = right["name"]
|
||||
if js_is_int_name(lname) {
|
||||
if js_is_int_name(rname) {
|
||||
return "(" + left_c + " !== " + right_c + ")"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if left_kind == "Str" { return "!str_eq(" + left_c + ", " + right_c + ")" }
|
||||
if right_kind == "Str" { return "!str_eq(" + left_c + ", " + right_c + ")" }
|
||||
return "(" + left_c + " !== " + right_c + ")"
|
||||
}
|
||||
|
||||
let op_c: String = js_binop(op)
|
||||
return "(" + left_c + " " + op_c + " " + right_c + ")"
|
||||
}
|
||||
|
||||
if kind == "Call" {
|
||||
let func = expr["func"]
|
||||
let args = expr["args"]
|
||||
let arity: Int = native_list_len(args)
|
||||
let func_kind: String = func["expr"]
|
||||
|
||||
let args_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < arity {
|
||||
let arg = native_list_get(args, i)
|
||||
let arg_c: String = js_cg_expr(arg)
|
||||
let args_parts = native_list_append(args_parts, arg_c)
|
||||
let i = i + 1
|
||||
}
|
||||
let args_c: String = str_join(args_parts, ", ")
|
||||
|
||||
if func_kind == "Ident" {
|
||||
let fn_name: String = func["name"]
|
||||
return fn_name + "(" + args_c + ")"
|
||||
}
|
||||
|
||||
if func_kind == "Field" {
|
||||
// El's `obj.method(args)` becomes `method(obj, args)` — same
|
||||
// convention as the C backend. The runtime exports method
|
||||
// shortforms (append, len, get, map_get, map_set) that match.
|
||||
let obj = func["object"]
|
||||
let field: String = func["field"]
|
||||
let obj_c: String = js_cg_expr(obj)
|
||||
if arity > 0 {
|
||||
return field + "(" + obj_c + ", " + args_c + ")"
|
||||
}
|
||||
return field + "(" + obj_c + ")"
|
||||
}
|
||||
|
||||
let fn_c: String = js_cg_expr(func)
|
||||
return fn_c + "(" + args_c + ")"
|
||||
}
|
||||
|
||||
if kind == "Field" {
|
||||
// El's `obj.foo` becomes JS `obj["foo"]` — works on plain objects
|
||||
// (maps) and on JS objects with prototype. el_get_field is a
|
||||
// runtime helper for callers that want EL_NULL on missing keys.
|
||||
let obj = expr["object"]
|
||||
let field: String = expr["field"]
|
||||
let obj_c: String = js_cg_expr(obj)
|
||||
return "el_get_field(" + obj_c + ", " + js_str_lit(field) + ")"
|
||||
}
|
||||
|
||||
if kind == "Index" {
|
||||
// Map vs list dispatch on the index expression kind, same as C.
|
||||
let obj = expr["object"]
|
||||
let idx = expr["index"]
|
||||
let obj_c: String = js_cg_expr(obj)
|
||||
let idx_c: String = js_cg_expr(idx)
|
||||
let idx_kind: String = idx["expr"]
|
||||
if str_eq(idx_kind, "Str") {
|
||||
return "el_get_field(" + obj_c + ", " + idx_c + ")"
|
||||
}
|
||||
return "el_list_get(" + obj_c + ", " + idx_c + ")"
|
||||
}
|
||||
|
||||
if kind == "Array" {
|
||||
let elems = expr["elems"]
|
||||
let n: Int = native_list_len(elems)
|
||||
if n == 0 { return "[]" }
|
||||
let items_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let elem = native_list_get(elems, i)
|
||||
let elem_c: String = js_cg_expr(elem)
|
||||
let items_parts = native_list_append(items_parts, elem_c)
|
||||
let i = i + 1
|
||||
}
|
||||
return "[" + str_join(items_parts, ", ") + "]"
|
||||
}
|
||||
|
||||
if kind == "Map" {
|
||||
let pairs = expr["pairs"]
|
||||
let n: Int = native_list_len(pairs)
|
||||
if n == 0 { return "{}" }
|
||||
let items_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let pair = native_list_get(pairs, i)
|
||||
let key: String = pair["key"]
|
||||
let val = pair["value"]
|
||||
let val_c: String = js_cg_expr(val)
|
||||
let items_parts = native_list_append(items_parts, js_str_lit(key) + ": " + val_c)
|
||||
let i = i + 1
|
||||
}
|
||||
return "{" + str_join(items_parts, ", ") + "}"
|
||||
}
|
||||
|
||||
if kind == "Try" {
|
||||
let inner = expr["inner"]
|
||||
return js_cg_expr(inner)
|
||||
}
|
||||
|
||||
if kind == "If" {
|
||||
let cond = expr["cond"]
|
||||
let cond_c: String = js_cg_expr(cond)
|
||||
// If as expression: ternary. Body of the if-expression is not
|
||||
// currently emitted as expression-form for compound bodies; this
|
||||
// matches the C backend's if-expr stub.
|
||||
return "(" + cond_c + " ? 1 : 0)"
|
||||
}
|
||||
|
||||
if kind == "Match" {
|
||||
return js_cg_match(expr)
|
||||
}
|
||||
|
||||
"null"
|
||||
}
|
||||
|
||||
// ── Match codegen (basic) ─────────────────────────────────────────────────────
|
||||
//
|
||||
// Lower a match expression to an IIFE with if/else chain. Works for
|
||||
// LitInt / LitStr / LitBool / Wildcard / Binding patterns. Tagged-union
|
||||
// destructuring is not implemented — it's stubbed and falls through to
|
||||
// the wildcard path.
|
||||
|
||||
fn js_next_match_id() -> String {
|
||||
let csv: String = state_get("__js_match_counter")
|
||||
let n = 0
|
||||
if !str_eq(csv, "") {
|
||||
let n = str_to_int(csv)
|
||||
}
|
||||
let n = n + 1
|
||||
state_set("__js_match_counter", native_int_to_str(n))
|
||||
native_int_to_str(n)
|
||||
}
|
||||
|
||||
fn js_cg_match(expr: Map<String, Any>) -> String {
|
||||
let subject = expr["subject"]
|
||||
let arms = expr["arms"]
|
||||
let subj_c: String = js_cg_expr(subject)
|
||||
let id: String = js_next_match_id()
|
||||
let subj_var: String = "_match_subj_" + id
|
||||
let parts: [String] = native_list_empty()
|
||||
let parts = native_list_append(parts, "((" + subj_var + ") => { ")
|
||||
let n: Int = native_list_len(arms)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let arm = native_list_get(arms, i)
|
||||
let pat = arm["pattern"]
|
||||
let body = arm["body"]
|
||||
let pkind: String = pat["pattern"]
|
||||
let body_c: String = js_cg_expr(body)
|
||||
if str_eq(pkind, "Wildcard") {
|
||||
let parts = native_list_append(parts, "return (" + body_c + "); ")
|
||||
} else {
|
||||
if str_eq(pkind, "Binding") {
|
||||
let bname: String = pat["name"]
|
||||
let parts = native_list_append(parts, "{ const " + bname + " = " + subj_var + "; return (" + body_c + "); } ")
|
||||
} else {
|
||||
if str_eq(pkind, "LitInt") {
|
||||
let v: String = pat["value"]
|
||||
let parts = native_list_append(parts, "if (" + subj_var + " === " + v + ") return (" + body_c + "); ")
|
||||
} else {
|
||||
if str_eq(pkind, "LitStr") {
|
||||
let v: String = pat["value"]
|
||||
let parts = native_list_append(parts, "if (str_eq(" + subj_var + ", " + js_str_lit(v) + ")) return (" + body_c + "); ")
|
||||
} else {
|
||||
if str_eq(pkind, "LitBool") {
|
||||
let v: String = pat["value"]
|
||||
let bv = "false"
|
||||
if str_eq(v, "true") { let bv = "true" }
|
||||
let parts = native_list_append(parts, "if (" + subj_var + " === " + bv + ") return (" + body_c + "); ")
|
||||
} else {
|
||||
// unknown pattern → wildcard
|
||||
let parts = native_list_append(parts, "return (" + body_c + "); ")
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
let parts = native_list_append(parts, "return null; })(" + subj_c + ")")
|
||||
str_join(parts, "")
|
||||
}
|
||||
|
||||
// ── Variable scope tracking ───────────────────────────────────────────────────
|
||||
//
|
||||
// El allows `let x = ...` to redeclare in the same scope. JS would throw
|
||||
// with `let` (Identifier already declared). We track declared names and
|
||||
// emit bare `x = ...` on redeclaration, `let x = ...` first time.
|
||||
|
||||
fn js_list_contains(lst: [String], s: String) -> Bool {
|
||||
let n: Int = native_list_len(lst)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let item: String = native_list_get(lst, i)
|
||||
if item == s { return true }
|
||||
let i = i + 1
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
// ── Statement codegen ─────────────────────────────────────────────────────────
|
||||
|
||||
fn js_cg_stmt(stmt: Map<String, Any>, indent: String, declared: [String]) -> [String] {
|
||||
let kind: String = stmt["stmt"]
|
||||
|
||||
if kind == "Let" {
|
||||
let name: String = stmt["name"]
|
||||
let val = stmt["value"]
|
||||
let val_c: String = js_cg_expr(val)
|
||||
let ltype: String = stmt["type"]
|
||||
if str_eq(ltype, "Int") {
|
||||
js_add_int_name(name)
|
||||
}
|
||||
let vk: String = val["expr"]
|
||||
if str_eq(vk, "Int") {
|
||||
js_add_int_name(name)
|
||||
}
|
||||
if js_list_contains(declared, name) {
|
||||
js_emit_line(indent + name + " = " + val_c + ";")
|
||||
return declared
|
||||
} else {
|
||||
// Use `let` (not `const`) — El semantics allow rebinding.
|
||||
js_emit_line(indent + "let " + name + " = " + val_c + ";")
|
||||
return native_list_append(declared, name)
|
||||
}
|
||||
}
|
||||
|
||||
if kind == "Return" {
|
||||
let val = stmt["value"]
|
||||
let val_kind: String = val["expr"]
|
||||
if val_kind == "Nil" {
|
||||
js_emit_line(indent + "return null;")
|
||||
} else {
|
||||
let val_c: String = js_cg_expr(val)
|
||||
js_emit_line(indent + "return " + val_c + ";")
|
||||
}
|
||||
return declared
|
||||
}
|
||||
|
||||
// Bare reassignment: `name = expr`. Mirrors the C backend — emits a
|
||||
// plain JS assignment without `let` so we don't shadow an outer binding.
|
||||
if kind == "Assign" {
|
||||
let name: String = stmt["name"]
|
||||
let val = stmt["value"]
|
||||
let val_c: String = js_cg_expr(val)
|
||||
js_emit_line(indent + name + " = " + val_c + ";")
|
||||
return declared
|
||||
}
|
||||
|
||||
if kind == "Expr" {
|
||||
let val = stmt["value"]
|
||||
let val_kind: String = val["expr"]
|
||||
if val_kind == "If" {
|
||||
js_cg_if_stmt(val, indent, declared)
|
||||
return declared
|
||||
}
|
||||
if val_kind == "For" {
|
||||
js_cg_for_stmt(val, indent, declared)
|
||||
return declared
|
||||
}
|
||||
let val_c: String = js_cg_expr(val)
|
||||
js_emit_line(indent + val_c + ";")
|
||||
return declared
|
||||
}
|
||||
|
||||
if kind == "While" {
|
||||
let cond = stmt["cond"]
|
||||
let body = stmt["body"]
|
||||
let cond_c: String = js_cg_expr(cond)
|
||||
let cond_c = js_strip_outer_parens(cond_c)
|
||||
js_emit_line(indent + "while (" + cond_c + ") {")
|
||||
js_cg_stmts(body, indent + " ", native_list_clone(declared))
|
||||
js_emit_line(indent + "}")
|
||||
return declared
|
||||
}
|
||||
|
||||
if kind == "For" {
|
||||
let item: String = stmt["item"]
|
||||
let list_expr = stmt["list"]
|
||||
let body = stmt["body"]
|
||||
js_cg_for_body(item, list_expr, body, indent, declared)
|
||||
return declared
|
||||
}
|
||||
|
||||
if kind == "FnDef" { return declared }
|
||||
if kind == "TypeDef" { return declared }
|
||||
if kind == "EnumDef" { return declared }
|
||||
if kind == "Import" { return declared }
|
||||
if kind == "CgiBlock" {
|
||||
// CGI blocks compile to a no-op + warning comment in JS target.
|
||||
// The runtime cgi identity is server-side; UI code is not a CGI
|
||||
// principal. See spec/codegen-js.md §7.
|
||||
let cname: String = stmt["name"]
|
||||
js_emit_line(indent + "// cgi block '" + cname + "' — no-op in JS target (server-side concept)")
|
||||
return declared
|
||||
}
|
||||
if kind == "ServiceBlock" {
|
||||
let sname: String = stmt["name"]
|
||||
js_emit_line(indent + "// service block '" + sname + "' — no-op in JS target")
|
||||
return declared
|
||||
}
|
||||
declared
|
||||
}
|
||||
|
||||
// Strip a single layer of surrounding parentheses from a JS expression string.
|
||||
fn js_strip_outer_parens(s: String) -> String {
|
||||
let chars: [String] = native_string_chars(s)
|
||||
let n: Int = native_list_len(chars)
|
||||
if n < 2 { return s }
|
||||
let first: String = native_list_get(chars, 0)
|
||||
let last: String = native_list_get(chars, n - 1)
|
||||
if first == "(" {
|
||||
if last == ")" {
|
||||
let depth = 1
|
||||
let i = 1
|
||||
let balanced = true
|
||||
while i < n - 1 {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if ch == "(" {
|
||||
let depth = depth + 1
|
||||
}
|
||||
if ch == ")" {
|
||||
let depth = depth - 1
|
||||
if depth == 0 {
|
||||
let balanced = false
|
||||
let i = n
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
if balanced {
|
||||
return str_slice(s, 1, n - 1)
|
||||
}
|
||||
}
|
||||
}
|
||||
s
|
||||
}
|
||||
|
||||
fn js_cg_if_stmt(expr: Map<String, Any>, indent: String, declared: [String]) -> Void {
|
||||
let cond = expr["cond"]
|
||||
let then_stmts = expr["then"]
|
||||
let else_stmts = expr["else"]
|
||||
let has_else: Bool = expr["has_else"]
|
||||
let cond_c: String = js_cg_expr(cond)
|
||||
let cond_c = js_strip_outer_parens(cond_c)
|
||||
js_emit_line(indent + "if (" + cond_c + ") {")
|
||||
js_cg_stmts(then_stmts, indent + " ", native_list_clone(declared))
|
||||
if has_else {
|
||||
js_emit_line(indent + "} else {")
|
||||
js_cg_stmts(else_stmts, indent + " ", native_list_clone(declared))
|
||||
}
|
||||
js_emit_line(indent + "}")
|
||||
}
|
||||
|
||||
fn js_cg_for_body(item: String, list_expr: Map<String, Any>, body: [Map<String, Any>], indent: String, declared: [String]) -> Void {
|
||||
let list_c: String = js_cg_expr(list_expr)
|
||||
js_emit_line(indent + "for (const " + item + " of " + list_c + ") {")
|
||||
let body_decl = native_list_clone(declared)
|
||||
let body_decl = native_list_append(body_decl, item)
|
||||
js_cg_stmts(body, indent + " ", body_decl)
|
||||
js_emit_line(indent + "}")
|
||||
}
|
||||
|
||||
fn js_cg_for_stmt(expr: Map<String, Any>, indent: String, declared: [String]) -> Void {
|
||||
let item: String = expr["item"]
|
||||
let list_expr = expr["list"]
|
||||
let body = expr["body"]
|
||||
js_cg_for_body(item, list_expr, body, indent, declared)
|
||||
}
|
||||
|
||||
fn js_cg_stmts(stmts: [Map<String, Any>], indent: String, declared: [String]) -> [String] {
|
||||
let n: Int = native_list_len(stmts)
|
||||
let i = 0
|
||||
let decl = declared
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
let decl = js_cg_stmt(stmt, indent, decl)
|
||||
let i = i + 1
|
||||
}
|
||||
decl
|
||||
}
|
||||
|
||||
// ── Function declaration codegen ──────────────────────────────────────────────
|
||||
|
||||
fn js_params_str(params: [Map<String, Any>]) -> String {
|
||||
let n: Int = native_list_len(params)
|
||||
if n == 0 { return "" }
|
||||
let parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let param = native_list_get(params, i)
|
||||
let name: String = param["name"]
|
||||
let parts = native_list_append(parts, name)
|
||||
let i = i + 1
|
||||
}
|
||||
str_join(parts, ", ")
|
||||
}
|
||||
|
||||
// Same implicit-return transform as the C backend.
|
||||
fn js_transform_implicit_return(body: [Map<String, Any>]) -> [Map<String, Any>] {
|
||||
let n: Int = native_list_len(body)
|
||||
if n == 0 { return body }
|
||||
let last: Map<String, Any> = native_list_get(body, n - 1)
|
||||
let last_kind: String = last["stmt"]
|
||||
if last_kind == "Expr" {
|
||||
let val = last["value"]
|
||||
let val_kind: String = val["expr"]
|
||||
if val_kind == "If" { return body }
|
||||
if val_kind == "For" { return body }
|
||||
let new_body: [Map<String, Any>] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n - 1 {
|
||||
let new_body = native_list_append(new_body, native_list_get(body, i))
|
||||
let i = i + 1
|
||||
}
|
||||
let return_stmt: Map<String, Any> = { "stmt": "Return", "value": val }
|
||||
let new_body = native_list_append(new_body, return_stmt)
|
||||
return new_body
|
||||
}
|
||||
body
|
||||
}
|
||||
|
||||
fn js_cg_fn(stmt: Map<String, Any>) -> Void {
|
||||
let fn_name: String = stmt["name"]
|
||||
let params = stmt["params"]
|
||||
let body = stmt["body"]
|
||||
let ret_type: String = stmt["ret_type"]
|
||||
let params_str: String = js_params_str(params)
|
||||
js_build_int_names_for_params(params)
|
||||
|
||||
// Special-case `fn main` — emit as a regular function and call it
|
||||
// at module bottom (after all top-level statements). This matches
|
||||
// the C backend's behavior where `fn main` is the entry point.
|
||||
if fn_name == "main" {
|
||||
js_emit_line("function main(" + params_str + ") {")
|
||||
} else {
|
||||
js_emit_line("function " + fn_name + "(" + params_str + ") {")
|
||||
}
|
||||
|
||||
let decl = native_list_empty()
|
||||
let np: Int = native_list_len(params)
|
||||
let pi = 0
|
||||
while pi < np {
|
||||
let param = native_list_get(params, pi)
|
||||
let pname: String = param["name"]
|
||||
let decl = native_list_append(decl, pname)
|
||||
let pi = pi + 1
|
||||
}
|
||||
let body_xformed = body
|
||||
if !str_eq(ret_type, "Void") {
|
||||
let body_xformed = js_transform_implicit_return(body)
|
||||
}
|
||||
js_cg_stmts(body_xformed, " ", decl)
|
||||
js_emit_line("}")
|
||||
js_emit_blank()
|
||||
}
|
||||
|
||||
// ── Top-level codegen ─────────────────────────────────────────────────────────
|
||||
|
||||
fn js_is_fndef(stmt: Map<String, Any>) -> Bool {
|
||||
let kind: String = stmt["stmt"]
|
||||
if kind == "FnDef" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
fn js_is_top_level_decl(stmt: Map<String, Any>) -> Bool {
|
||||
let kind: String = stmt["stmt"]
|
||||
if kind == "TypeDef" { return true }
|
||||
if kind == "EnumDef" { return true }
|
||||
if kind == "Import" { return true }
|
||||
if kind == "CgiBlock" { return true }
|
||||
if kind == "ServiceBlock" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
// ── Entry point ───────────────────────────────────────────────────────────────
|
||||
|
||||
fn codegen_js(stmts: [Map<String, Any>], source: String) -> String {
|
||||
// Reset per-compile state.
|
||||
state_set("__js_int_names", "")
|
||||
state_set("__js_match_counter", "")
|
||||
|
||||
// Preamble: inline the runtime via a single import that side-effects
|
||||
// globalThis. The runtime path is resolved relative to the generated
|
||||
// output; users running `elc --target=js` are responsible for ensuring
|
||||
// el_runtime.js is reachable. For self-contained output, the runtime
|
||||
// could be inlined; that is a follow-up.
|
||||
js_emit_line("// Generated by elc --target=js")
|
||||
js_emit_line("// Runtime: foundation/el/el-compiler/runtime/el_runtime.js")
|
||||
js_emit_line("import \"./el_runtime.js\";")
|
||||
js_emit_line("const {")
|
||||
js_emit_line(" println, print, el_str_concat, str_concat, str_eq, str_starts_with, str_ends_with,")
|
||||
js_emit_line(" str_len, int_to_str, str_to_int, str_slice, str_contains, str_replace,")
|
||||
js_emit_line(" str_to_upper, str_to_lower, str_trim, str_index_of, str_split, str_char_at,")
|
||||
js_emit_line(" str_char_code, str_lower, str_upper, el_abs, el_max, el_min,")
|
||||
js_emit_line(" el_list_new, el_list_len, el_list_get, el_list_append, el_list_empty, el_list_clone,")
|
||||
js_emit_line(" list_push, list_join, list_range,")
|
||||
js_emit_line(" el_map_new, el_get_field, el_map_get, el_map_set,")
|
||||
js_emit_line(" http_get, http_post, http_post_json,")
|
||||
js_emit_line(" fs_read, fs_write, fs_list,")
|
||||
js_emit_line(" json_parse, json_stringify, json_get, json_get_string, json_get_int,")
|
||||
js_emit_line(" time_now, time_now_utc, sleep_ms, bool_to_str, exit_program,")
|
||||
js_emit_line(" el_retain, el_release,")
|
||||
js_emit_line(" append, len, get, map_get, map_set,")
|
||||
js_emit_line(" native_list_get, native_list_len, native_list_append, native_list_empty,")
|
||||
js_emit_line(" native_list_clone, native_string_chars, native_int_to_str,")
|
||||
js_emit_line(" args, state_set, state_get, state_del, state_keys, env,")
|
||||
js_emit_line(" dharma_connect, dharma_send, dharma_emit, dharma_field, dharma_activate,")
|
||||
js_emit_line(" engram_node, engram_search, engram_activate,")
|
||||
js_emit_line(" llm_call, llm_call_system,")
|
||||
js_emit_line("} = globalThis.__el;")
|
||||
js_emit_blank()
|
||||
|
||||
// Function definitions
|
||||
let n: Int = native_list_len(stmts)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
if js_is_fndef(stmt) {
|
||||
js_cg_fn(stmt)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Top-level statements (those that are not FnDef and not declarative)
|
||||
// run at module load. If the program defines `fn main`, we additionally
|
||||
// call main() at the end so the C-backend mental model of "fn main is
|
||||
// the entry point" carries over.
|
||||
let has_main = false
|
||||
let i = 0
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
let sk: String = stmt["stmt"]
|
||||
if str_eq(sk, "FnDef") {
|
||||
let fn_name: String = stmt["name"]
|
||||
if str_eq(fn_name, "main") {
|
||||
let has_main = true
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
let main_decl = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
if js_is_fndef(stmt) {
|
||||
// skip
|
||||
} else {
|
||||
if js_is_top_level_decl(stmt) {
|
||||
// skip
|
||||
} else {
|
||||
let main_decl = js_cg_stmt(stmt, "", main_decl)
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
if has_main {
|
||||
js_emit_blank()
|
||||
js_emit_line("main();")
|
||||
}
|
||||
|
||||
// Return empty string — output was streamed via println
|
||||
""
|
||||
}
|
||||
+294
-147
@@ -1,4 +1,4 @@
|
||||
// codegen.el — El compiler C source code generator
|
||||
// codegen.el - El compiler C source code generator
|
||||
//
|
||||
// Input: list of AST statement maps (from parser.el)
|
||||
// Output: C source printed to stdout (streamed, one line at a time)
|
||||
@@ -7,37 +7,90 @@
|
||||
// Functions map directly to C functions; top-level statements become main().
|
||||
//
|
||||
// Entry point: fn codegen(stmts: [Map<String, Any>], source: String) -> String
|
||||
// Returns "" — output goes to stdout via println().
|
||||
// Returns "" - output goes to stdout via println().
|
||||
//
|
||||
// Streaming output avoids O(n²) string concatenation: each emitted line is
|
||||
// Streaming output avoids O(n-) string concatenation: each emitted line is
|
||||
// printed immediately rather than appended to a growing string.
|
||||
|
||||
// ── String helpers ────────────────────────────────────────────────────────────
|
||||
// -- String helpers ------------------------------------------------------------
|
||||
|
||||
// Escape a C string literal (double-quotes and backslashes).
|
||||
// Hex-encode a single nibble (0-15) as a lowercase hex character.
|
||||
fn nibble_to_hex(n: Int) -> String {
|
||||
str_char_at("0123456789abcdef", n)
|
||||
}
|
||||
|
||||
// Encode a byte value (0-255) as a two-character hex string.
|
||||
fn byte_to_hex2(b: Int) -> String {
|
||||
let hi: Int = (b / 16)
|
||||
let lo: Int = (b - hi * 16)
|
||||
nibble_to_hex(hi) + nibble_to_hex(lo)
|
||||
}
|
||||
|
||||
// Return true if the byte value is a C hex digit (0-9, a-f, A-F).
|
||||
// Used to determine whether a \xNN escape needs a string-literal split
|
||||
// to prevent the C preprocessor from greedily consuming following hex chars.
|
||||
fn is_hex_digit_byte(b: Int) -> Bool {
|
||||
if b >= 48 { if b <= 57 { return true } } // 0-9
|
||||
if b >= 65 { if b <= 70 { return true } } // A-F
|
||||
if b >= 97 { if b <= 102 { return true } } // a-f
|
||||
false
|
||||
}
|
||||
|
||||
fn c_escape(s: String) -> String {
|
||||
let chars: [String] = native_string_chars(s)
|
||||
let total: Int = native_list_len(chars)
|
||||
let out = ""
|
||||
let i = 0
|
||||
// Use index-based byte scanning via str_char_code(s, i) and str_char_at(s, i).
|
||||
// This avoids native_string_chars + str_join, which corrupts high-byte (>= 0x80)
|
||||
// characters because list_join's looks_like_string heuristic rejects strings
|
||||
// whose first byte is >= 0x7F and emits them as decimal pointer values instead.
|
||||
//
|
||||
// IMPORTANT: after a \xNN hex escape, if the next byte is a hex digit
|
||||
// (0-9, a-f, A-F), we emit `""` to split the C string literal so the C
|
||||
// compiler does not greedily read extra hex digits as part of the escape.
|
||||
// E.g. "\xad" followed by "bamos" must become "\xad" "bamos" because 'b'
|
||||
// is a hex digit and C would otherwise read "\xadb" (= 0xADB, out of range).
|
||||
let total: Int = str_len(s)
|
||||
let parts: [String] = native_list_empty()
|
||||
let i: Int = 0
|
||||
let prev_was_hex_escape: Bool = false
|
||||
while i < total {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if ch == "\"" {
|
||||
let out = out + "\\\""
|
||||
let bval: Int = str_char_code(s, i)
|
||||
// If the previous token was a \xNN escape and the current byte is a
|
||||
// hex digit, insert an empty string literal ("") to break the escape.
|
||||
if prev_was_hex_escape {
|
||||
if is_hex_digit_byte(bval) {
|
||||
let parts = native_list_append(parts, "\"\"")
|
||||
}
|
||||
}
|
||||
let prev_was_hex_escape = false
|
||||
if bval == 34 {
|
||||
// 34 = '"'
|
||||
let parts = native_list_append(parts, "\\\"")
|
||||
} else {
|
||||
if ch == "\\" {
|
||||
let out = out + "\\\\"
|
||||
if bval == 92 {
|
||||
// 92 = '\\'
|
||||
let parts = native_list_append(parts, "\\\\")
|
||||
} else {
|
||||
if ch == "\n" {
|
||||
let out = out + "\\n"
|
||||
if bval == 10 {
|
||||
// 10 = '\n'
|
||||
let parts = native_list_append(parts, "\\n")
|
||||
} else {
|
||||
if ch == "\r" {
|
||||
let out = out + "\\r"
|
||||
if bval == 13 {
|
||||
// 13 = '\r'
|
||||
let parts = native_list_append(parts, "\\r")
|
||||
} else {
|
||||
if ch == "\t" {
|
||||
let out = out + "\\t"
|
||||
if bval == 9 {
|
||||
// 9 = '\t'
|
||||
let parts = native_list_append(parts, "\\t")
|
||||
} else {
|
||||
let out = out + ch
|
||||
if bval >= 128 {
|
||||
// Escape non-ASCII bytes (>= 0x80) as \xNN so
|
||||
// Clang does not misinterpret multi-byte UTF-8
|
||||
// sequences in C string literals.
|
||||
let parts = native_list_append(parts, "\\x" + byte_to_hex2(bval))
|
||||
let prev_was_hex_escape = true
|
||||
} else {
|
||||
let parts = native_list_append(parts, str_char_at(s, i))
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -45,14 +98,14 @@ fn c_escape(s: String) -> String {
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
out
|
||||
str_join(parts, "")
|
||||
}
|
||||
|
||||
fn c_str_lit(s: String) -> String {
|
||||
"\"" + c_escape(s) + "\""
|
||||
}
|
||||
|
||||
// ── Type mapping ──────────────────────────────────────────────────────────────
|
||||
// -- Type mapping --------------------------------------------------------------
|
||||
|
||||
fn el_type_to_c(type_str: String) -> String {
|
||||
if type_str == "String" { return "const char*" }
|
||||
@@ -64,7 +117,7 @@ fn el_type_to_c(type_str: String) -> String {
|
||||
"void*"
|
||||
}
|
||||
|
||||
// ── Code emission ─────────────────────────────────────────────────────────────
|
||||
// -- Code emission -------------------------------------------------------------
|
||||
//
|
||||
// emit_line/emit_blank stream output directly via println.
|
||||
// This avoids building a large string in memory.
|
||||
@@ -77,7 +130,7 @@ fn emit_blank() -> Void {
|
||||
println("")
|
||||
}
|
||||
|
||||
// ── Operator helpers ──────────────────────────────────────────────────────────
|
||||
// -- Operator helpers ----------------------------------------------------------
|
||||
|
||||
fn binop_to_c(op: String) -> String {
|
||||
if op == "Plus" { return "+" }
|
||||
@@ -95,11 +148,11 @@ fn binop_to_c(op: String) -> String {
|
||||
op
|
||||
}
|
||||
|
||||
// ── Expression codegen ────────────────────────────────────────────────────────
|
||||
// -- Expression codegen --------------------------------------------------------
|
||||
//
|
||||
// cg_expr returns a C expression string (not a statement).
|
||||
|
||||
// duration_unit_nanos — multiplier from a postfix-literal unit name to
|
||||
// duration_unit_nanos - multiplier from a postfix-literal unit name to
|
||||
// nanoseconds. Singular and plural forms collapse to the same multiplier;
|
||||
// the parser already restricted `unit` to the set is_duration_unit accepts.
|
||||
// Returns the multiplier as a decimal string suitable for splicing into
|
||||
@@ -130,7 +183,7 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
return v
|
||||
}
|
||||
|
||||
// DurationLit — postfix-literal time value (e.g. 30.seconds, 1.hour).
|
||||
// DurationLit - postfix-literal time value (e.g. 30.seconds, 1.hour).
|
||||
// Lowered to a literal int64 nanosecond count, wrapped in the runtime
|
||||
// entry point so the intent is explicit at the C level. The arithmetic
|
||||
// is fully constant-folded by any optimising C compiler.
|
||||
@@ -144,7 +197,7 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
if kind == "Float" {
|
||||
// Wrap Float literals in el_from_float() so the bit pattern is
|
||||
// preserved through the el_val_t (int64) slot. Without this,
|
||||
// implicit double→int64 conversion in C truncates `0.8` to `0`
|
||||
// implicit double->int64 conversion in C truncates `0.8` to `0`
|
||||
// when passed to a builtin that expects el_val_t.
|
||||
let v: String = expr["value"]
|
||||
return "el_from_float(" + v + ")"
|
||||
@@ -191,7 +244,26 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
let left_kind: String = left["expr"]
|
||||
let right_kind: String = right["expr"]
|
||||
|
||||
// ── Temporal-type dispatch (Instant + Duration first-class) ────────
|
||||
// -- String/equality fast-path: skip O(N-) temporal traversals --------
|
||||
// The 10 temporal predicates below each recurse into the left subtree:
|
||||
// O(depth) state_get calls per predicate, O(N-) total for a chain of N
|
||||
// string-concat BinOps (e.g. the 70-100-part HTML chains in soul.el).
|
||||
// When either operand is a bare Str literal the result is always concat
|
||||
// or str_eq - no temporal dispatch is possible. Exit immediately.
|
||||
if str_eq(op, "Plus") {
|
||||
if str_eq(left_kind, "Str") { return "el_str_concat(" + left_c + ", " + right_c + ")" }
|
||||
if str_eq(right_kind, "Str") { return "el_str_concat(" + left_c + ", " + right_c + ")" }
|
||||
}
|
||||
if str_eq(op, "EqEq") {
|
||||
if str_eq(left_kind, "Str") { return "str_eq(" + left_c + ", " + right_c + ")" }
|
||||
if str_eq(right_kind, "Str") { return "str_eq(" + left_c + ", " + right_c + ")" }
|
||||
}
|
||||
if str_eq(op, "NotEq") {
|
||||
if str_eq(left_kind, "Str") { return "!str_eq(" + left_c + ", " + right_c + ")" }
|
||||
if str_eq(right_kind, "Str") { return "!str_eq(" + left_c + ", " + right_c + ")" }
|
||||
}
|
||||
|
||||
// -- Temporal-type dispatch (Instant + Duration first-class) --------
|
||||
// Run BEFORE the int / string / generic paths so typed temporal
|
||||
// operands route through the runtime wrappers and invalid combos
|
||||
// become #error directives rather than silently falling through to
|
||||
@@ -377,7 +449,7 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
if right_is_dur { return "el_duration_ne(" + left_c + ", " + right_c + ")" }
|
||||
}
|
||||
}
|
||||
// Fall through — let the existing path handle anything we
|
||||
// Fall through - let the existing path handle anything we
|
||||
// didn't explicitly cover (typically string-concat with a
|
||||
// typed temporal value, e.g. for debug prints, which works
|
||||
// because both share the int64 slot).
|
||||
@@ -396,7 +468,7 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
// builtin, or BinOp arithmetic over Ints) participates in
|
||||
// arithmetic, not string concat. Recursion into BinOp lets
|
||||
// `a + b + c` (chained Int adds) and `acc * 16 + d` route to
|
||||
// arithmetic instead of falling to el_str_concat — both sides
|
||||
// arithmetic instead of falling to el_str_concat - both sides
|
||||
// are Int so the outer `+` is too.
|
||||
if is_int_expr(left) {
|
||||
if is_int_expr(right) {
|
||||
@@ -417,7 +489,7 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
return "(" + left_c + " " + op_c + " " + right_c + ")"
|
||||
}
|
||||
// Otherwise: BinOp(+) with a Call/Ident side without int-typed
|
||||
// evidence — fall back to string concat (the historical default).
|
||||
// evidence - fall back to string concat (the historical default).
|
||||
if left_kind == "Call" {
|
||||
return "el_str_concat(" + left_c + ", " + right_c + ")"
|
||||
}
|
||||
@@ -449,7 +521,7 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
// identifiers tracked in __int_names (typed Int via `let x: Int = ...`).
|
||||
// Without the int-name check, `seen == idx` between two Int locals
|
||||
// miscompiles to str_eq(seen, idx), strcmp'ing what are integer values
|
||||
// dressed as char* — segfault on the first non-printable byte.
|
||||
// dressed as char* - segfault on the first non-printable byte.
|
||||
if op == "EqEq" {
|
||||
if left_kind == "Int" {
|
||||
return "(" + left_c + " == " + right_c + ")"
|
||||
@@ -565,17 +637,15 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
let arity: Int = native_list_len(args)
|
||||
let func_kind: String = func["expr"]
|
||||
|
||||
let args_c = ""
|
||||
let args_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < arity {
|
||||
let arg = native_list_get(args, i)
|
||||
let arg_c: String = cg_expr(arg)
|
||||
if i > 0 {
|
||||
let args_c = args_c + ", "
|
||||
}
|
||||
let args_c = args_c + arg_c
|
||||
let args_parts = native_list_append(args_parts, arg_c)
|
||||
let i = i + 1
|
||||
}
|
||||
let args_c: String = str_join(args_parts, ", ")
|
||||
|
||||
if func_kind == "Ident" {
|
||||
let fn_name: String = func["name"]
|
||||
@@ -585,17 +655,17 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
// violations to be emitted as #error directives at the
|
||||
// top of the generated C, so cc fails with a clear msg.
|
||||
cap_check_call(fn_name)
|
||||
// Arity check against the builtin table — refuse, with a clear
|
||||
// Arity check against the builtin table - refuse, with a clear
|
||||
// El-source message, when a known builtin gets the wrong arg
|
||||
// count (e.g. `http_serve(port)` instead of `http_serve(port,
|
||||
// handler)`). User-defined fns and variadic builtins pass
|
||||
// through (builtin_arity returns -1).
|
||||
arity_check_call(fn_name, arity)
|
||||
// sleep(Duration) — Phase 1 of the typed-time work. When the
|
||||
// sleep(Duration) - Phase 1 of the typed-time work. When the
|
||||
// single arg is provably a Duration we lower to el_sleep_duration
|
||||
// so the runtime sees nanos directly. Existing sleep() callers
|
||||
// that pass an Int still emit `sleep(<int>)`, which falls through
|
||||
// to the no-such-symbol path — those call sites must migrate to
|
||||
// to the no-such-symbol path - those call sites must migrate to
|
||||
// a typed Duration. Acceptable: the spec marks them out for an
|
||||
// audit pass during Phase 1.
|
||||
if str_eq(fn_name, "sleep") {
|
||||
@@ -606,6 +676,20 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
}
|
||||
}
|
||||
}
|
||||
// el_from_float takes a raw C double - do not wrap the float
|
||||
// argument in el_from_float() again. Without this, the float
|
||||
// literal codegen (which wraps every Float in el_from_float())
|
||||
// produces el_from_float(el_from_float(0.7)) - double-encoded.
|
||||
if str_eq(fn_name, "el_from_float") {
|
||||
if arity == 1 {
|
||||
let only_arg = native_list_get(args, 0)
|
||||
let arg_kind: String = only_arg["expr"]
|
||||
if str_eq(arg_kind, "Float") {
|
||||
let v: String = only_arg["value"]
|
||||
return "el_from_float(" + v + ")"
|
||||
}
|
||||
}
|
||||
}
|
||||
return fn_name + "(" + args_c + ")"
|
||||
}
|
||||
|
||||
@@ -639,8 +723,8 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
// El programs use `t["field"]` for map access and `arr[i]` for
|
||||
// list access. The parser emits the same Index node for both.
|
||||
// Dispatch at codegen time on the index expression kind: string-
|
||||
// literal index → map field access (`el_get_field`); anything
|
||||
// else → list element access (`el_list_get`).
|
||||
// literal index -> map field access (`el_get_field`); anything
|
||||
// else -> list element access (`el_list_get`).
|
||||
let obj = expr["object"]
|
||||
let idx = expr["index"]
|
||||
let obj_c: String = cg_expr(obj)
|
||||
@@ -658,18 +742,15 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
// Empty literal: el_list_new(0, ) generates malformed C (trailing
|
||||
// comma in a varargs call). Emit el_list_empty() directly.
|
||||
if n == 0 { return "el_list_empty()" }
|
||||
let items = ""
|
||||
let items_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let elem = native_list_get(elems, i)
|
||||
let elem_c: String = cg_expr(elem)
|
||||
if i > 0 {
|
||||
let items = items + ", "
|
||||
}
|
||||
let items = items + elem_c
|
||||
let items_parts = native_list_append(items_parts, elem_c)
|
||||
let i = i + 1
|
||||
}
|
||||
return "el_list_new(" + native_int_to_str(n) + ", " + items + ")"
|
||||
return "el_list_new(" + native_int_to_str(n) + ", " + str_join(items_parts, ", ") + ")"
|
||||
}
|
||||
|
||||
if kind == "Map" {
|
||||
@@ -677,23 +758,20 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
let n: Int = native_list_len(pairs)
|
||||
// Empty literal: `el_map_new(0, )` is malformed C (trailing comma in
|
||||
// a varargs call). Emit `el_map_new(0)` directly so empty-map
|
||||
// shadowing inside for/while/if bodies — `let acc: Map = {}` —
|
||||
// shadowing inside for/while/if bodies - `let acc: Map = {}` -
|
||||
// doesn't fail downstream cc with parse errors.
|
||||
if n == 0 { return "el_map_new(0)" }
|
||||
let items = ""
|
||||
let items_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let pair = native_list_get(pairs, i)
|
||||
let key: String = pair["key"]
|
||||
let val = pair["value"]
|
||||
let val_c: String = cg_expr(val)
|
||||
if i > 0 {
|
||||
let items = items + ", "
|
||||
}
|
||||
let items = items + c_str_lit(key) + ", " + val_c
|
||||
let items_parts = native_list_append(items_parts, c_str_lit(key) + ", " + val_c)
|
||||
let i = i + 1
|
||||
}
|
||||
return "el_map_new(" + native_int_to_str(n) + ", " + items + ")"
|
||||
return "el_map_new(" + native_int_to_str(n) + ", " + str_join(items_parts, ", ") + ")"
|
||||
}
|
||||
|
||||
if kind == "Try" {
|
||||
@@ -712,7 +790,7 @@ fn cg_expr(expr: Map<String, Any>) -> String {
|
||||
"EL_NULL"
|
||||
}
|
||||
|
||||
// ── Match codegen ─────────────────────────────────────────────────────────────
|
||||
// -- Match codegen -------------------------------------------------------------
|
||||
//
|
||||
// Lower a match expression to a GCC/Clang statement-expression.
|
||||
// A unique label suffix is allocated per match via state_set("__match_counter").
|
||||
@@ -736,7 +814,9 @@ fn cg_match(expr: Map<String, Any>) -> String {
|
||||
let subj_var: String = "_match_subj_" + id
|
||||
let result_var: String = "_match_result_" + id
|
||||
let done_label: String = "_match_done_" + id
|
||||
let out: String = "({ el_val_t " + subj_var + " = " + subj_c + "; el_val_t " + result_var + " = 0; "
|
||||
// Accumulate arm fragments into a list to avoid O(n-) string growth.
|
||||
let parts: [String] = native_list_empty()
|
||||
let parts = native_list_append(parts, "({ el_val_t " + subj_var + " = " + subj_c + "; el_val_t " + result_var + " = 0; ")
|
||||
let n: Int = native_list_len(arms)
|
||||
let i = 0
|
||||
while i < n {
|
||||
@@ -746,19 +826,19 @@ fn cg_match(expr: Map<String, Any>) -> String {
|
||||
let pkind: String = pat["pattern"]
|
||||
let body_c: String = cg_expr(body)
|
||||
if str_eq(pkind, "Wildcard") {
|
||||
let out = out + "{ " + result_var + " = (" + body_c + "); goto " + done_label + "; } "
|
||||
let parts = native_list_append(parts, "{ " + result_var + " = (" + body_c + "); goto " + done_label + "; } ")
|
||||
} else {
|
||||
if str_eq(pkind, "Binding") {
|
||||
let bname: String = pat["name"]
|
||||
let out = out + "{ el_val_t " + bname + " = " + subj_var + "; " + result_var + " = (" + body_c + "); goto " + done_label + "; } "
|
||||
let parts = native_list_append(parts, "{ el_val_t " + bname + " = " + subj_var + "; " + result_var + " = (" + body_c + "); goto " + done_label + "; } ")
|
||||
} else {
|
||||
if str_eq(pkind, "LitInt") {
|
||||
let v: String = pat["value"]
|
||||
let out = out + "if (" + subj_var + " == " + v + ") { " + result_var + " = (" + body_c + "); goto " + done_label + "; } "
|
||||
let parts = native_list_append(parts, "if (" + subj_var + " == " + v + ") { " + result_var + " = (" + body_c + "); goto " + done_label + "; } ")
|
||||
} else {
|
||||
if str_eq(pkind, "LitStr") {
|
||||
let v: String = pat["value"]
|
||||
let out = out + "if (str_eq(" + subj_var + ", EL_STR(" + c_str_lit(v) + "))) { " + result_var + " = (" + body_c + "); goto " + done_label + "; } "
|
||||
let parts = native_list_append(parts, "if (str_eq(" + subj_var + ", EL_STR(" + c_str_lit(v) + "))) { " + result_var + " = (" + body_c + "); goto " + done_label + "; } ")
|
||||
} else {
|
||||
if str_eq(pkind, "LitBool") {
|
||||
let v: String = pat["value"]
|
||||
@@ -766,10 +846,10 @@ fn cg_match(expr: Map<String, Any>) -> String {
|
||||
if str_eq(v, "true") {
|
||||
let bv = "1"
|
||||
}
|
||||
let out = out + "if (" + subj_var + " == " + bv + ") { " + result_var + " = (" + body_c + "); goto " + done_label + "; } "
|
||||
let parts = native_list_append(parts, "if (" + subj_var + " == " + bv + ") { " + result_var + " = (" + body_c + "); goto " + done_label + "; } ")
|
||||
} else {
|
||||
// unknown pattern → wildcard
|
||||
let out = out + "{ " + result_var + " = (" + body_c + "); goto " + done_label + "; } "
|
||||
// unknown pattern -> wildcard
|
||||
let parts = native_list_append(parts, "{ " + result_var + " = (" + body_c + "); goto " + done_label + "; } ")
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -777,11 +857,11 @@ fn cg_match(expr: Map<String, Any>) -> String {
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
let out = out + done_label + ":; " + result_var + "; })"
|
||||
out
|
||||
let parts = native_list_append(parts, done_label + ":; " + result_var + "; })")
|
||||
str_join(parts, "")
|
||||
}
|
||||
|
||||
// ── If-as-expression codegen ─────────────────────────────────────────────────
|
||||
// -- If-as-expression codegen -------------------------------------------------
|
||||
//
|
||||
// Lower `if cond { thenBody } else { elseBody }` used in expression position
|
||||
// (e.g. `let x = if a { b } else { c }`) to a GCC/Clang statement-expression
|
||||
@@ -809,7 +889,8 @@ fn next_if_id() -> String {
|
||||
// result var stays at its initial 0.
|
||||
fn cg_if_expr_arm(stmts: [Map<String, Any>], result_var: String) -> String {
|
||||
let n: Int = native_list_len(stmts)
|
||||
let out = ""
|
||||
// Collect statement fragments into a list to avoid O(n-) string growth.
|
||||
let parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let s = native_list_get(stmts, i)
|
||||
@@ -820,31 +901,31 @@ fn cg_if_expr_arm(stmts: [Map<String, Any>], result_var: String) -> String {
|
||||
let name: String = s["name"]
|
||||
let val = s["value"]
|
||||
let val_c: String = cg_expr(val)
|
||||
let out = out + "el_val_t " + name + " = " + val_c + "; "
|
||||
let parts = native_list_append(parts, "el_val_t " + name + " = " + val_c + "; ")
|
||||
} else {
|
||||
if str_eq(sk, "Return") {
|
||||
let val = s["value"]
|
||||
let val_c: String = cg_expr(val)
|
||||
let out = out + result_var + " = (" + val_c + "); "
|
||||
let parts = native_list_append(parts, result_var + " = (" + val_c + "); ")
|
||||
} else {
|
||||
if str_eq(sk, "Expr") {
|
||||
let val = s["value"]
|
||||
let val_c: String = cg_expr(val)
|
||||
if is_last {
|
||||
let out = out + result_var + " = (" + val_c + "); "
|
||||
let parts = native_list_append(parts, result_var + " = (" + val_c + "); ")
|
||||
} else {
|
||||
let out = out + "(void)(" + val_c + "); "
|
||||
let parts = native_list_append(parts, "(void)(" + val_c + "); ")
|
||||
}
|
||||
} else {
|
||||
if str_eq(sk, "Assign") {
|
||||
// Real reassignment in an expression-position arm —
|
||||
// Real reassignment in an expression-position arm -
|
||||
// emit the store; the arm's "value" stays whatever
|
||||
// result_var was last set to, which is the El
|
||||
// semantics (assignment is a statement, not a value).
|
||||
let aname: String = s["name"]
|
||||
let aval = s["value"]
|
||||
let aval_c: String = cg_expr(aval)
|
||||
let out = out + aname + " = " + aval_c + "; "
|
||||
let parts = native_list_append(parts, aname + " = " + aval_c + "; ")
|
||||
} else {
|
||||
// Non-trivial stmt kinds (While/For) shouldn't appear in
|
||||
// expression-position arm bodies; emit nothing rather
|
||||
@@ -855,7 +936,7 @@ fn cg_if_expr_arm(stmts: [Map<String, Any>], result_var: String) -> String {
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
out
|
||||
str_join(parts, "")
|
||||
}
|
||||
|
||||
fn cg_if_expr(expr: Map<String, Any>) -> String {
|
||||
@@ -875,7 +956,7 @@ fn cg_if_expr(expr: Map<String, Any>) -> String {
|
||||
out
|
||||
}
|
||||
|
||||
// ── Variable scope tracking ───────────────────────────────────────────────────
|
||||
// -- Variable scope tracking ---------------------------------------------------
|
||||
//
|
||||
// El allows `let x = expr` to both declare and reassign x in the same scope.
|
||||
// C doesn't allow redeclaring the same name in the same block.
|
||||
@@ -894,7 +975,7 @@ fn list_contains(lst: [String], s: String) -> Bool {
|
||||
false
|
||||
}
|
||||
|
||||
// ── Statement codegen ─────────────────────────────────────────────────────────
|
||||
// -- Statement codegen ---------------------------------------------------------
|
||||
//
|
||||
// cg_stmt emits C lines via println. declared is a list of already-declared
|
||||
// variable names in the current C scope; returns updated declared list.
|
||||
@@ -943,7 +1024,7 @@ fn cg_stmt(stmt: Map<String, Any>, indent: String, declared: [String]) -> [Strin
|
||||
if str_eq(ltype, "Zone") {
|
||||
add_zone_name(name)
|
||||
}
|
||||
// Inference from RHS — duration literals and known-typed calls
|
||||
// Inference from RHS - duration literals and known-typed calls
|
||||
// propagate even when the let is unannotated.
|
||||
if is_instant_expr(val) {
|
||||
add_instant_name(name)
|
||||
@@ -998,7 +1079,7 @@ fn cg_stmt(stmt: Map<String, Any>, indent: String, declared: [String]) -> [Strin
|
||||
}
|
||||
|
||||
// Bare reassignment: `name = expr`. Always emits a plain C assignment
|
||||
// (no `el_val_t` prefix) — by construction the parser only produces
|
||||
// (no `el_val_t` prefix) - by construction the parser only produces
|
||||
// Assign for an existing identifier. If the name happens NOT to be in
|
||||
// `declared` for the current C scope (it was let-bound by an enclosing
|
||||
// block) the emit still resolves at C level because the variable lives
|
||||
@@ -1033,7 +1114,7 @@ fn cg_stmt(stmt: Map<String, Any>, indent: String, declared: [String]) -> [Strin
|
||||
let cond_c: String = cg_expr(cond)
|
||||
let cond_c = strip_outer_parens(cond_c)
|
||||
emit_line(indent + "while (" + cond_c + ") {")
|
||||
// Body lives in its own C block — clone so let-bindings inside the
|
||||
// Body lives in its own C block - clone so let-bindings inside the
|
||||
// loop don't leak into the parent's `declared` list (which would make
|
||||
// a sibling scope's `let x` emit assignment on an undeclared name).
|
||||
cg_stmts(body, indent + " ", native_list_clone(declared))
|
||||
@@ -1053,6 +1134,7 @@ fn cg_stmt(stmt: Map<String, Any>, indent: String, declared: [String]) -> [Strin
|
||||
if kind == "TypeDef" { return declared }
|
||||
if kind == "EnumDef" { return declared }
|
||||
if kind == "Import" { return declared }
|
||||
if kind == "ExternFn" { return declared }
|
||||
if kind == "CgiBlock" { return declared }
|
||||
declared
|
||||
}
|
||||
@@ -1084,14 +1166,7 @@ fn strip_outer_parens(s: String) -> String {
|
||||
let i = i + 1
|
||||
}
|
||||
if balanced {
|
||||
let inner = ""
|
||||
let j = 1
|
||||
while j < n - 1 {
|
||||
let ch: String = native_list_get(chars, j)
|
||||
let inner = inner + ch
|
||||
let j = j + 1
|
||||
}
|
||||
return inner
|
||||
return str_slice(s, 1, n - 1)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1106,7 +1181,7 @@ fn cg_if_stmt(expr: Map<String, Any>, indent: String, declared: [String]) -> Voi
|
||||
let cond_c: String = cg_expr(cond)
|
||||
let cond_c = strip_outer_parens(cond_c)
|
||||
emit_line(indent + "if (" + cond_c + ") {")
|
||||
// Each branch gets its own clone of `declared` — variables let-bound
|
||||
// Each branch gets its own clone of `declared` - variables let-bound
|
||||
// inside the then/else block live only in that C scope, and must not
|
||||
// leak back to the parent (or to the sibling branch) through shared
|
||||
// list mutation. Cheap shallow copy; the entries (variable name strings)
|
||||
@@ -1158,7 +1233,7 @@ fn cg_stmts(stmts: [Map<String, Any>], indent: String, declared: [String]) -> [S
|
||||
decl
|
||||
}
|
||||
|
||||
// ── Function declaration codegen ───────────────────────────────────────────────
|
||||
// -- Function declaration codegen -----------------------------------------------
|
||||
|
||||
fn param_decl(param: Map<String, Any>, idx: Int) -> String {
|
||||
let name: String = param["name"]
|
||||
@@ -1168,18 +1243,15 @@ fn param_decl(param: Map<String, Any>, idx: Int) -> String {
|
||||
fn params_to_c(params: [Map<String, Any>]) -> String {
|
||||
let n: Int = native_list_len(params)
|
||||
if n == 0 { return "void" }
|
||||
let out = ""
|
||||
let parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let param = native_list_get(params, i)
|
||||
let decl: String = param_decl(param, i)
|
||||
if i > 0 {
|
||||
let out = out + ", "
|
||||
}
|
||||
let out = out + decl
|
||||
let parts = native_list_append(parts, decl)
|
||||
let i = i + 1
|
||||
}
|
||||
out
|
||||
str_join(parts, ", ")
|
||||
}
|
||||
|
||||
// Transform a function body so that an implicit-return final expression
|
||||
@@ -1230,7 +1302,7 @@ fn is_int_name(name: String) -> Bool {
|
||||
|
||||
// Same shape as is_int_name, for Instant- and Duration-typed bindings.
|
||||
// Used by the BinOp/comparison codegen to dispatch arithmetic through the
|
||||
// typed runtime wrappers (el_instant_add_dur, el_duration_lt, …) and to
|
||||
// typed runtime wrappers (el_instant_add_dur, el_duration_lt, -) and to
|
||||
// surface mismatches (Instant + Instant, Duration + Int) as #error
|
||||
// directives at the top of the generated C.
|
||||
fn is_instant_name(name: String) -> Bool {
|
||||
@@ -1292,7 +1364,7 @@ fn is_int_call(call_expr: Map<String, Any>) -> Bool {
|
||||
}
|
||||
|
||||
// Builtins that return an Instant. Used by is_instant_expr and the BinOp
|
||||
// dispatch — `now() + 5.seconds` types as Instant only because we can see
|
||||
// dispatch - `now() + 5.seconds` types as Instant only because we can see
|
||||
// that now() is an Instant-returning Call.
|
||||
fn is_instant_call(call_expr: Map<String, Any>) -> Bool {
|
||||
let func = call_expr["func"]
|
||||
@@ -1328,7 +1400,7 @@ fn is_duration_call(call_expr: Map<String, Any>) -> Bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// Phase 1.5 — Calendar / CalendarTime / Rhythm / LocalDate / LocalTime /
|
||||
// Phase 1.5 - Calendar / CalendarTime / Rhythm / LocalDate / LocalTime /
|
||||
// LocalDateTime / Zone are first-class boxed types. Each has its own name
|
||||
// set in process state, populated from typed `let` bindings and parameter
|
||||
// annotations. The BinOp dispatcher consults these to forbid mismatched
|
||||
@@ -1516,7 +1588,7 @@ fn is_zone_expr(expr: Map<String, Any>) -> Bool {
|
||||
// Recursive type predicates for Instant / Duration. Mirror is_int_expr.
|
||||
// is_instant_expr / is_duration_expr return true only when the expression
|
||||
// is provably of that type at codegen time. Anything ambiguous returns
|
||||
// false — the BinOp dispatcher then leaves the expression on the
|
||||
// false - the BinOp dispatcher then leaves the expression on the
|
||||
// untyped-int path, which is the safest fallback because at the runtime
|
||||
// level all three types share the int64 slot.
|
||||
fn is_instant_expr(expr: Map<String, Any>) -> Bool {
|
||||
@@ -1531,8 +1603,8 @@ fn is_instant_expr(expr: Map<String, Any>) -> Bool {
|
||||
if str_eq(k, "BinOp") {
|
||||
let op: String = expr["op"]
|
||||
if str_eq(op, "Plus") {
|
||||
// Instant + Duration → Instant
|
||||
// Duration + Instant → Instant
|
||||
// Instant + Duration -> Instant
|
||||
// Duration + Instant -> Instant
|
||||
if is_instant_expr(expr["left"]) {
|
||||
if is_duration_expr(expr["right"]) { return true }
|
||||
}
|
||||
@@ -1542,7 +1614,7 @@ fn is_instant_expr(expr: Map<String, Any>) -> Bool {
|
||||
return false
|
||||
}
|
||||
if str_eq(op, "Minus") {
|
||||
// Instant - Duration → Instant
|
||||
// Instant - Duration -> Instant
|
||||
if is_instant_expr(expr["left"]) {
|
||||
if is_duration_expr(expr["right"]) { return true }
|
||||
}
|
||||
@@ -1569,15 +1641,15 @@ fn is_duration_expr(expr: Map<String, Any>) -> Bool {
|
||||
if str_eq(k, "BinOp") {
|
||||
let op: String = expr["op"]
|
||||
if str_eq(op, "Plus") {
|
||||
// Duration + Duration → Duration
|
||||
// Duration + Duration -> Duration
|
||||
if is_duration_expr(expr["left"]) {
|
||||
if is_duration_expr(expr["right"]) { return true }
|
||||
}
|
||||
return false
|
||||
}
|
||||
if str_eq(op, "Minus") {
|
||||
// Duration - Duration → Duration
|
||||
// Instant - Instant → Duration (caught here, not in is_instant_expr)
|
||||
// Duration - Duration -> Duration
|
||||
// Instant - Instant -> Duration (caught here, not in is_instant_expr)
|
||||
if is_duration_expr(expr["left"]) {
|
||||
if is_duration_expr(expr["right"]) { return true }
|
||||
}
|
||||
@@ -1587,8 +1659,8 @@ fn is_duration_expr(expr: Map<String, Any>) -> Bool {
|
||||
return false
|
||||
}
|
||||
if str_eq(op, "Star") {
|
||||
// Duration * Int → Duration
|
||||
// Int * Duration → Duration
|
||||
// Duration * Int -> Duration
|
||||
// Int * Duration -> Duration
|
||||
if is_duration_expr(expr["left"]) {
|
||||
if is_int_expr(expr["right"]) { return true }
|
||||
}
|
||||
@@ -1598,7 +1670,7 @@ fn is_duration_expr(expr: Map<String, Any>) -> Bool {
|
||||
return false
|
||||
}
|
||||
if str_eq(op, "Slash") {
|
||||
// Duration / Int → Duration
|
||||
// Duration / Int -> Duration
|
||||
if is_duration_expr(expr["left"]) {
|
||||
if is_int_expr(expr["right"]) { return true }
|
||||
}
|
||||
@@ -1629,13 +1701,13 @@ fn time_record_violation(kind: String, detail: String) -> Bool {
|
||||
// the outer dispatch only checks the immediate kind, not the inner.
|
||||
//
|
||||
// Rules:
|
||||
// Int literal → Int
|
||||
// Ident in __int_names → Int
|
||||
// Call to known-Int builtin → Int
|
||||
// Neg of Int → Int
|
||||
// BinOp arithmetic of two Ints → Int (Plus, Minus, Star, Slash, Percent)
|
||||
// BinOp comparison/logical → Int (yields 0/1; safe to treat as Int)
|
||||
// anything else → not provably Int
|
||||
// Int literal -> Int
|
||||
// Ident in __int_names -> Int
|
||||
// Call to known-Int builtin -> Int
|
||||
// Neg of Int -> Int
|
||||
// BinOp arithmetic of two Ints -> Int (Plus, Minus, Star, Slash, Percent)
|
||||
// BinOp comparison/logical -> Int (yields 0/1; safe to treat as Int)
|
||||
// anything else -> not provably Int
|
||||
fn is_int_expr(expr: Map<String, Any>) -> Bool {
|
||||
let k: String = expr["expr"]
|
||||
if str_eq(k, "Int") { return true }
|
||||
@@ -1654,7 +1726,7 @@ fn is_int_expr(expr: Map<String, Any>) -> Bool {
|
||||
}
|
||||
if str_eq(k, "BinOp") {
|
||||
let op: String = expr["op"]
|
||||
// Comparisons and logicals always yield 0/1 — safe Int.
|
||||
// Comparisons and logicals always yield 0/1 - safe Int.
|
||||
if str_eq(op, "EqEq") { return true }
|
||||
if str_eq(op, "NotEq") { return true }
|
||||
if str_eq(op, "Lt") { return true }
|
||||
@@ -1663,7 +1735,7 @@ fn is_int_expr(expr: Map<String, Any>) -> Bool {
|
||||
if str_eq(op, "GtEq") { return true }
|
||||
if str_eq(op, "And") { return true }
|
||||
if str_eq(op, "Or") { return true }
|
||||
// Arithmetic propagates: Int op Int → Int.
|
||||
// Arithmetic propagates: Int op Int -> Int.
|
||||
if str_eq(op, "Plus") {
|
||||
if is_int_expr(expr["left"]) {
|
||||
if is_int_expr(expr["right"]) { return true }
|
||||
@@ -1693,7 +1765,7 @@ fn is_int_expr(expr: Map<String, Any>) -> Bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// ── Capability-kind enforcement ──────────────────────────────────────────────
|
||||
// -- Capability-kind enforcement ----------------------------------------------
|
||||
//
|
||||
// A program's top-level block (cgi / service / none) determines which
|
||||
// runtime primitives it may call. The compiler records violations in
|
||||
@@ -1702,11 +1774,11 @@ fn is_int_expr(expr: Map<String, Any>) -> Bool {
|
||||
// downstream cc step fails with a clear message.
|
||||
//
|
||||
// Capability tiers:
|
||||
// "cgi" — full self-formation. All primitives.
|
||||
// "service" — bounded. Cannot call self-formation primitives:
|
||||
// "cgi" - full self-formation. All primitives.
|
||||
// "service" - bounded. Cannot call self-formation primitives:
|
||||
// llm_call_agentic, llm_register_tool, dharma_emit,
|
||||
// dharma_field. Single-turn LLM calls are allowed.
|
||||
// "utility" — default. No DHARMA, no LLM. Pure compute + I/O.
|
||||
// "utility" - default. No DHARMA, no LLM. Pure compute + I/O.
|
||||
//
|
||||
// The compiler-level rule is structural: the binary either CAN or CANNOT
|
||||
// emit the call. There is no runtime check, no opt-in, no override.
|
||||
@@ -1721,7 +1793,7 @@ fn cap_record_violation(kind: String, fn_name: String) -> Bool {
|
||||
return true
|
||||
}
|
||||
|
||||
// Self-formation primitives — the cut between CGI and service. A program
|
||||
// Self-formation primitives - the cut between CGI and service. A program
|
||||
// that emits these calls IS structurally a CGI; we forbid them everywhere
|
||||
// else.
|
||||
fn is_self_formation_call(fn_name: String) -> Bool {
|
||||
@@ -1732,7 +1804,7 @@ fn is_self_formation_call(fn_name: String) -> Bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// Any DHARMA primitive — utilities have zero network presence.
|
||||
// Any DHARMA primitive - utilities have zero network presence.
|
||||
fn is_dharma_call(fn_name: String) -> Bool {
|
||||
if str_eq(fn_name, "dharma_connect") { return true }
|
||||
if str_eq(fn_name, "dharma_send") { return true }
|
||||
@@ -1745,7 +1817,7 @@ fn is_dharma_call(fn_name: String) -> Bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// Any LLM primitive — utilities have no LLM access at all.
|
||||
// Any LLM primitive - utilities have no LLM access at all.
|
||||
fn is_llm_call(fn_name: String) -> Bool {
|
||||
if str_eq(fn_name, "llm_call") { return true }
|
||||
if str_eq(fn_name, "llm_call_system") { return true }
|
||||
@@ -1795,14 +1867,14 @@ fn emit_cap_violations() -> Void {
|
||||
if colon > 0 {
|
||||
let kind: String = str_slice(entry, 0, colon)
|
||||
let fn_name: String = str_slice(entry, colon + 1, str_len(entry))
|
||||
emit_line("#error \"capability violation: '" + kind + "' programs may not call '" + fn_name + "' (self-formation primitive — only 'cgi' programs may use it)\"")
|
||||
emit_line("#error \"capability violation: '" + kind + "' programs may not call '" + fn_name + "' (self-formation primitive - only 'cgi' programs may use it)\"")
|
||||
}
|
||||
let i = i + next_comma + 1
|
||||
}
|
||||
}
|
||||
|
||||
// Surface temporal-type violations as #error directives. The cg_expr BinOp
|
||||
// dispatcher records each violation (Instant + Instant, Duration + Int, …)
|
||||
// dispatcher records each violation (Instant + Instant, Duration + Int, -)
|
||||
// as a CSV entry "kind:detail" via time_record_violation. Each entry maps
|
||||
// to a single #error so downstream cc fails the build with a clear El-
|
||||
// source-level message before the bogus C even links.
|
||||
@@ -1825,7 +1897,7 @@ fn emit_time_violations() -> Void {
|
||||
}
|
||||
}
|
||||
|
||||
// ── Builtin arity table ───────────────────────────────────────────────────────
|
||||
// -- Builtin arity table -------------------------------------------------------
|
||||
//
|
||||
// El programs sometimes call runtime builtins with the wrong number of
|
||||
// arguments (e.g. `http_serve(port)` instead of `http_serve(port, handler)`).
|
||||
@@ -1835,7 +1907,7 @@ fn emit_time_violations() -> Void {
|
||||
//
|
||||
// Strategy: a small static table mirrors el_runtime.h. Variadic builtins
|
||||
// (el_list_new, el_map_new, args) and unknown identifiers (user fns,
|
||||
// dynamic dispatch) return -1 → no check. A mismatch records a violation
|
||||
// dynamic dispatch) return -1 -> no check. A mismatch records a violation
|
||||
// in process state, which emit_arity_violations() turns into #error
|
||||
// directives at the top of the generated C.
|
||||
fn builtin_arity(name: String) -> Int {
|
||||
@@ -2039,7 +2111,7 @@ fn builtin_arity(name: String) -> Int {
|
||||
if str_eq(name, "get") { return 2 }
|
||||
if str_eq(name, "map_get") { return 2 }
|
||||
if str_eq(name, "map_set") { return 3 }
|
||||
// -1 sentinel: variadic / unknown / user-defined → no check.
|
||||
// -1 sentinel: variadic / unknown / user-defined -> no check.
|
||||
return -1
|
||||
}
|
||||
|
||||
@@ -2237,7 +2309,7 @@ fn build_int_names_for_params(params: [Map<String, Any>]) -> Bool {
|
||||
|
||||
fn cg_fn(stmt: Map<String, Any>) -> Void {
|
||||
let fn_name: String = stmt["name"]
|
||||
// Skip El's `fn main()` — C provides its own main() for top-level stmts
|
||||
// Skip El's `fn main()` - C provides its own main() for top-level stmts
|
||||
// and a duplicate `el_val_t main(void)` would collide with it.
|
||||
if fn_name == "main" { return }
|
||||
let params = stmt["params"]
|
||||
@@ -2269,8 +2341,8 @@ fn cg_fn(stmt: Map<String, Any>) -> Void {
|
||||
}
|
||||
// Lift the final bare expression into an explicit return so implicit
|
||||
// returns ("fn lex(s) { ... tokens }") actually return their value.
|
||||
// Void-returning functions skip this — wrapping `println(x)` in
|
||||
// `return …` is a C type error.
|
||||
// Void-returning functions skip this - wrapping `println(x)` in
|
||||
// `return -` is a C type error.
|
||||
let body_xformed = body
|
||||
if !str_eq(ret_type, "Void") {
|
||||
let body_xformed = transform_implicit_return(body)
|
||||
@@ -2281,7 +2353,7 @@ fn cg_fn(stmt: Map<String, Any>) -> Void {
|
||||
emit_blank()
|
||||
}
|
||||
|
||||
// ── Top-level codegen ─────────────────────────────────────────────────────────
|
||||
// -- Top-level codegen ---------------------------------------------------------
|
||||
|
||||
fn is_fndef(stmt: Map<String, Any>) -> Bool {
|
||||
let kind: String = stmt["stmt"]
|
||||
@@ -2295,6 +2367,7 @@ fn is_top_level_decl(stmt: Map<String, Any>) -> Bool {
|
||||
if kind == "EnumDef" { return true }
|
||||
if kind == "Import" { return true }
|
||||
if kind == "CgiBlock" { return true }
|
||||
if kind == "ExternFn" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
@@ -2306,7 +2379,7 @@ fn cgi_arg(value: String, has_value: Bool) -> String {
|
||||
return "EL_NULL"
|
||||
}
|
||||
|
||||
// ── VBD role enforcement ──────────────────────────────────────────────────────
|
||||
// -- VBD role enforcement ------------------------------------------------------
|
||||
//
|
||||
// Scan a function body for direct calls to DHARMA-restricted builtins
|
||||
// (dharma_emit, dharma_field). These may only appear inside @manager fns.
|
||||
@@ -2439,16 +2512,16 @@ fn vbd_has_restricted_call(stmts: [Map<String, Any>]) -> Bool {
|
||||
false
|
||||
}
|
||||
|
||||
// ── Entry point ────────────────────────────────────────────────────────────────
|
||||
// -- Entry point ----------------------------------------------------------------
|
||||
|
||||
fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
// Detect cgi/service blocks: at most one declarative top-level block.
|
||||
// The block determines the program's CAPABILITY KIND:
|
||||
// "cgi" — full self-formation. Calls all primitives.
|
||||
// "service" — bounded. Cannot call self-formation primitives
|
||||
// "cgi" - full self-formation. Calls all primitives.
|
||||
// "service" - bounded. Cannot call self-formation primitives
|
||||
// (llm_call_agentic, llm_register_tool, dharma_emit,
|
||||
// dharma_field, mindlink-creation).
|
||||
// "utility" — default; no DHARMA membership, no LLM, no agentic.
|
||||
// "utility" - default; no DHARMA membership, no LLM, no agentic.
|
||||
// Codegen enforces this with #error directives at every restricted
|
||||
// call site. The capability boundary is structural: a binary either
|
||||
// CAN or CANNOT do a thing, and the compiler decides at emission time.
|
||||
@@ -2483,7 +2556,7 @@ fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
}
|
||||
if cgi_count >= 1 {
|
||||
if svc_count >= 1 {
|
||||
emit_line("#error \"El: program declares both cgi and service blocks (mutually exclusive — pick one)\"")
|
||||
emit_line("#error \"El: program declares both cgi and service blocks (mutually exclusive - pick one)\"")
|
||||
}
|
||||
}
|
||||
// Stash the program kind so cg_expr's Call branch can enforce
|
||||
@@ -2503,9 +2576,44 @@ fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
emit_line("#include <stdint.h>")
|
||||
emit_line("#include <stdlib.h>")
|
||||
emit_line("#include \"el_runtime.h\"")
|
||||
|
||||
// Cross-module forward declarations: for each imported module, emit
|
||||
// #include "module.elh" so Clang sees the function signatures from
|
||||
// that module without needing the full source inlined. The .elh files
|
||||
// are generated by `elc --emit-header` and live in the same dist/
|
||||
// directory as the generated .c files. We use basename only (strip
|
||||
// the directory prefix and .el extension) so the include resolves
|
||||
// correctly regardless of the source tree layout.
|
||||
let imp_n: Int = native_list_len(stmts)
|
||||
let imp_i = 0
|
||||
while imp_i < imp_n {
|
||||
let imp_stmt = native_list_get(stmts, imp_i)
|
||||
let imp_kind: String = imp_stmt["stmt"]
|
||||
if str_eq(imp_kind, "Import") {
|
||||
let imp_path: String = imp_stmt["path"]
|
||||
// Extract basename: find last '/' and strip from there.
|
||||
let imp_path_len: Int = str_len(imp_path)
|
||||
let imp_last_slash: Int = -1
|
||||
let imp_j: Int = 0
|
||||
while imp_j < imp_path_len {
|
||||
let imp_c: String = str_slice(imp_path, imp_j, imp_j + 1)
|
||||
if str_eq(imp_c, "/") { let imp_last_slash = imp_j }
|
||||
let imp_j = imp_j + 1
|
||||
}
|
||||
let imp_base: String = str_slice(imp_path, imp_last_slash + 1, imp_path_len)
|
||||
// Strip .el extension if present.
|
||||
let imp_base_len: Int = str_len(imp_base)
|
||||
let imp_bname: String = imp_base
|
||||
if str_ends_with(imp_base, ".el") {
|
||||
let imp_bname = str_slice(imp_base, 0, imp_base_len - 3)
|
||||
}
|
||||
emit_line("#include \"" + imp_bname + ".elh\"")
|
||||
}
|
||||
let imp_i = imp_i + 1
|
||||
}
|
||||
emit_blank()
|
||||
|
||||
// Forward declarations (skip `main` — C provides its own)
|
||||
// Forward declarations (skip `main` - C provides its own)
|
||||
let n: Int = native_list_len(stmts)
|
||||
let i = 0
|
||||
while i < n {
|
||||
@@ -2519,11 +2627,17 @@ fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
emit_line("el_val_t " + fn_name + "(" + params_c + ");")
|
||||
}
|
||||
}
|
||||
if kind == "ExternFn" {
|
||||
let fn_name: String = stmt["name"]
|
||||
let params = stmt["params"]
|
||||
let params_c: String = params_to_c(params)
|
||||
emit_line("el_val_t " + fn_name + "(" + params_c + ");")
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
emit_blank()
|
||||
|
||||
// Top-level `let` bindings → file-scope storage. El programs use
|
||||
// Top-level `let` bindings -> file-scope storage. El programs use
|
||||
// top-level `let GREETING = "..."` as module constants that any
|
||||
// function below should be able to read. Without this pass, a top-
|
||||
// level Let only declares the name inside main()'s scope and any
|
||||
@@ -2557,6 +2671,36 @@ fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
emit_blank()
|
||||
}
|
||||
|
||||
// Detect whether this compilation unit has an entry point.
|
||||
// A unit is a library (no C main emitted) when there is no fn main()
|
||||
// and no top-level executable statements. This supports separate
|
||||
// compilation: library .c files contain only function definitions.
|
||||
let has_el_main = false
|
||||
let has_toplevel_stmts = false
|
||||
let i = 0
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
let sk: String = stmt["stmt"]
|
||||
if str_eq(sk, "FnDef") {
|
||||
let fn_name_chk: String = stmt["name"]
|
||||
if str_eq(fn_name_chk, "main") { let has_el_main = true }
|
||||
}
|
||||
if !is_fndef(stmt) {
|
||||
if !is_top_level_decl(stmt) {
|
||||
if !str_eq(sk, "Let") {
|
||||
let has_toplevel_stmts = true
|
||||
}
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
let is_library = false
|
||||
if !has_el_main {
|
||||
if !has_toplevel_stmts {
|
||||
let is_library = true
|
||||
}
|
||||
}
|
||||
|
||||
// Function definitions
|
||||
let i = 0
|
||||
while i < n {
|
||||
@@ -2567,6 +2711,9 @@ fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Skip C main() for library units (no fn main, no top-level stmts)
|
||||
if is_library { return "" }
|
||||
|
||||
// main(). Use _argc/_argv so El programs are free to declare their own
|
||||
// local `argv` / `argc` (compiler.el itself does this) without colliding
|
||||
// with the C-side parameters when fn main()'s body is folded in below.
|
||||
@@ -2638,7 +2785,7 @@ fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
let main_decl = cg_stmt(stmt, " ", main_decl)
|
||||
}
|
||||
}
|
||||
// Release AST node after final use — each stmt is fully processed
|
||||
// Release AST node after final use - each stmt is fully processed
|
||||
// by this point (forward decls, fn defs, top-level lets, and now
|
||||
// the main-body pass are all done). Releasing here prevents the
|
||||
// accumulated AST from exhausting memory on large source files.
|
||||
@@ -2661,16 +2808,16 @@ fn codegen(stmts: [Map<String, Any>], source: String) -> String {
|
||||
|
||||
// Emit any accumulated capability-violation #error directives. cc
|
||||
// will fail on the first one and surface the message; placement at
|
||||
// the bottom is fine — preprocessor errors halt the build wherever
|
||||
// the bottom is fine - preprocessor errors halt the build wherever
|
||||
// they appear.
|
||||
emit_cap_violations()
|
||||
// Same for builtin-arity violations: cc halts on the first #error,
|
||||
// so a misuse of a known builtin (wrong arg count) fails the build
|
||||
// with a clear message naming the builtin and its expected arity.
|
||||
emit_arity_violations()
|
||||
// Temporal-type violations (Instant + Instant, Duration + Int, …).
|
||||
// Temporal-type violations (Instant + Instant, Duration + Int, -).
|
||||
emit_time_violations()
|
||||
|
||||
// Return empty string — output was streamed via println
|
||||
// Return empty string - output was streamed via println
|
||||
""
|
||||
}
|
||||
|
||||
+106
-7
@@ -79,6 +79,74 @@ fn strip_flags(argv: [String]) -> [String] {
|
||||
return out
|
||||
}
|
||||
|
||||
// Detect --emit-header flag in argv.
|
||||
fn detect_emit_header(argv: [String]) -> Bool {
|
||||
let n: Int = native_list_len(argv)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let a: String = native_list_get(argv, i)
|
||||
if str_eq(a, "--emit-header") { return true }
|
||||
let i = i + 1
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Reconstruct an El type annotation string from a parsed type node.
|
||||
fn type_node_to_el(t: Map<String, Any>) -> String {
|
||||
let k: String = t["kind"]
|
||||
if str_eq(k, "Simple") { return t["name"] }
|
||||
if str_eq(k, "List") {
|
||||
let inner: String = type_node_to_el(t["inner"])
|
||||
return "[" + inner + "]"
|
||||
}
|
||||
if str_eq(k, "Map") {
|
||||
let kt: String = type_node_to_el(t["key"])
|
||||
let vt: String = type_node_to_el(t["val"])
|
||||
return "Map<" + kt + ", " + vt + ">"
|
||||
}
|
||||
"Any"
|
||||
}
|
||||
|
||||
// emit_header — write a .elh file from parsed statements.
|
||||
// Scans for FnDef nodes and emits 'extern fn' declarations.
|
||||
fn emit_header(stmts: [Map<String, Any>], hdr_path: String) -> Void {
|
||||
let n: Int = native_list_len(stmts)
|
||||
let i = 0
|
||||
let parts: [String] = native_list_empty()
|
||||
let parts = native_list_append(parts, "// auto-generated by elc --emit-header — do not edit\n")
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
let kind: String = stmt["stmt"]
|
||||
if str_eq(kind, "FnDef") {
|
||||
let name: String = stmt["name"]
|
||||
if !str_eq(name, "main") {
|
||||
let params = stmt["params"]
|
||||
let ret_type: String = stmt["ret_type"]
|
||||
// build param list
|
||||
let np: Int = native_list_len(params)
|
||||
let pi = 0
|
||||
let param_parts: [String] = native_list_empty()
|
||||
while pi < np {
|
||||
let param = native_list_get(params, pi)
|
||||
let pname: String = param["name"]
|
||||
let ptype: String = param["type"]
|
||||
if str_eq(ptype, "") { let ptype = "Any" }
|
||||
let param_parts = native_list_append(param_parts, pname + ": " + ptype)
|
||||
let pi = pi + 1
|
||||
}
|
||||
let params_str: String = str_join(param_parts, ", ")
|
||||
let ret_str: String = ret_type
|
||||
if str_eq(ret_str, "") { let ret_str = "Any" }
|
||||
let sig: String = "extern fn " + name + "(" + params_str + ") -> " + ret_str
|
||||
let parts = native_list_append(parts, sig + "\n")
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
let content: String = str_join(parts, "")
|
||||
let ok: Bool = fs_write(hdr_path, content)
|
||||
}
|
||||
|
||||
// ── Import resolution ────────────────────────────────────────────────────────
|
||||
//
|
||||
// elc supports two forms of import:
|
||||
@@ -135,6 +203,9 @@ fn parse_import_line(trimmed: String, dir: String) -> String {
|
||||
// source text with every imported module's body inlined ahead of the entry
|
||||
// source, deduplicated by absolute path. Uses state_set to track which paths
|
||||
// have already been pulled in for this run.
|
||||
//
|
||||
// Accumulates chunks into lists and joins once at the end to avoid the O(n²)
|
||||
// memory growth caused by repeated `prefix = prefix + chunk` concatenation.
|
||||
fn resolve_imports(src_path: String) -> String {
|
||||
let seen_key: String = "__elc_imp__:" + src_path
|
||||
let already: String = state_get(seen_key)
|
||||
@@ -146,22 +217,36 @@ fn resolve_imports(src_path: String) -> String {
|
||||
let lines: [String] = str_split(source, "\n")
|
||||
let n: Int = native_list_len(lines)
|
||||
|
||||
// First pass: pull in every import body ahead of this file's body.
|
||||
let prefix: String = ""
|
||||
let body: String = ""
|
||||
// Collect chunks into lists — O(1) amortized per append.
|
||||
// Join once at the end — O(n) single pass.
|
||||
let prefix_chunks: [String] = native_list_empty()
|
||||
let body_chunks: [String] = native_list_empty()
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let line: String = native_list_get(lines, i)
|
||||
let trimmed: String = str_trim(line)
|
||||
let imp_path: String = parse_import_line(trimmed, dir)
|
||||
if !str_eq(imp_path, "") {
|
||||
let prefix = prefix + resolve_imports(imp_path)
|
||||
// Use pre-compiled header if available (separate compilation).
|
||||
// Only check .elh for imported files — never for the entry file itself.
|
||||
let imp_elh_path: String = str_slice(imp_path, 0, str_len(imp_path) - 3) + ".elh"
|
||||
let imp_elh: String = fs_read(imp_elh_path)
|
||||
if !str_eq(imp_elh, "") {
|
||||
// Header exists: mark the .el as seen (so it won't be re-inlined
|
||||
// if something else also imports it) and use the header text.
|
||||
let seen_imp_key: String = "__elc_imp__:" + imp_path
|
||||
state_set(seen_imp_key, "1")
|
||||
let prefix_chunks = native_list_append(prefix_chunks, imp_elh)
|
||||
} else {
|
||||
let imp_body: String = resolve_imports(imp_path)
|
||||
let prefix_chunks = native_list_append(prefix_chunks, imp_body)
|
||||
}
|
||||
} else {
|
||||
let body = body + line + "\n"
|
||||
let body_chunks = native_list_append(body_chunks, line + "\n")
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return prefix + body
|
||||
return str_join(prefix_chunks, "") + str_join(body_chunks, "")
|
||||
}
|
||||
|
||||
// main — CLI entry point.
|
||||
@@ -176,13 +261,27 @@ fn main() -> Void {
|
||||
// (Section 1.5 of the language spec). detect_target itself is fine
|
||||
// because the function-name position has no token-class restriction.
|
||||
let tgt: String = detect_target(argv)
|
||||
let do_emit_header: Bool = detect_emit_header(argv)
|
||||
let positional: [String] = strip_flags(argv)
|
||||
let argc: Int = native_list_len(positional)
|
||||
if argc < 1 {
|
||||
println("el-compiler: usage: elc [--target=c|js] <source.el> [<output>]")
|
||||
println("el-compiler: usage: elc [--target=c|js] [--emit-header] <source.el> [<output>]")
|
||||
exit(1)
|
||||
}
|
||||
let src_path: String = native_list_get(positional, 0)
|
||||
|
||||
// When --emit-header is requested, parse the source file directly
|
||||
// (without inlining imports) and write out a .elh file alongside the .c.
|
||||
if do_emit_header {
|
||||
let raw_source: String = fs_read(src_path)
|
||||
let hdr_tokens: [Map<String, Any>] = lex(raw_source)
|
||||
let hdr_stmts: [Map<String, Any>] = parse(hdr_tokens)
|
||||
el_release(hdr_tokens)
|
||||
let hdr_path: String = str_slice(src_path, 0, str_len(src_path) - 3) + ".elh"
|
||||
emit_header(hdr_stmts, hdr_path)
|
||||
el_release(hdr_stmts)
|
||||
}
|
||||
|
||||
let source: String = resolve_imports(src_path)
|
||||
let out: String = compile_dispatch(tgt, source)
|
||||
if argc >= 2 {
|
||||
|
||||
+27
-26
@@ -146,6 +146,7 @@ fn keyword_kind(word: String) -> String {
|
||||
if word == "engine" { return "Engine" }
|
||||
if word == "accessor" { return "Accessor" }
|
||||
if word == "vessel" { return "Vessel" }
|
||||
if word == "extern" { return "Extern" }
|
||||
""
|
||||
}
|
||||
|
||||
@@ -156,7 +157,7 @@ fn keyword_kind(word: String) -> String {
|
||||
// Returns { "text": ..., "pos": i }
|
||||
fn scan_digits(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
let i = start
|
||||
let text = ""
|
||||
let parts: [String] = native_list_empty()
|
||||
let running = true
|
||||
while running {
|
||||
if i >= total {
|
||||
@@ -164,20 +165,20 @@ fn scan_digits(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
} else {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if lex_is_digit(ch) {
|
||||
let text = text + ch
|
||||
let parts = native_list_append(parts, ch)
|
||||
let i = i + 1
|
||||
} else {
|
||||
let running = false
|
||||
}
|
||||
}
|
||||
}
|
||||
{ "text": text, "pos": i }
|
||||
{ "text": str_join(parts, ""), "pos": i }
|
||||
}
|
||||
|
||||
// scan_ident — advance i while chars[i] is alphanumeric or underscore
|
||||
fn scan_ident(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
let i = start
|
||||
let text = ""
|
||||
let parts: [String] = native_list_empty()
|
||||
let running = true
|
||||
while running {
|
||||
if i >= total {
|
||||
@@ -185,14 +186,14 @@ fn scan_ident(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
} else {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if is_alnum_or_underscore(ch) {
|
||||
let text = text + ch
|
||||
let parts = native_list_append(parts, ch)
|
||||
let i = i + 1
|
||||
} else {
|
||||
let running = false
|
||||
}
|
||||
}
|
||||
}
|
||||
{ "text": text, "pos": i }
|
||||
{ "text": str_join(parts, ""), "pos": i }
|
||||
}
|
||||
|
||||
// ── Code-bearing string detection + comment strip ────────────────────────────
|
||||
@@ -253,7 +254,7 @@ fn looks_like_code(s: String) -> Bool {
|
||||
fn strip_code_comments(s: String) -> String {
|
||||
let chars: [String] = native_string_chars(s)
|
||||
let total: Int = native_list_len(chars)
|
||||
let out = ""
|
||||
let out_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
let in_squote = false
|
||||
let in_dquote = false
|
||||
@@ -269,11 +270,11 @@ fn strip_code_comments(s: String) -> String {
|
||||
if in_js_string {
|
||||
// Backslash escape: consume next char verbatim regardless of which.
|
||||
if ch == "\\" {
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let next_i = i + 1
|
||||
if next_i < total {
|
||||
let nc: String = native_list_get(chars, next_i)
|
||||
let out = out + nc
|
||||
let out_parts = native_list_append(out_parts, nc)
|
||||
let prev = nc
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
@@ -292,7 +293,7 @@ fn strip_code_comments(s: String) -> String {
|
||||
}
|
||||
}
|
||||
}
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
}
|
||||
@@ -308,7 +309,7 @@ fn strip_code_comments(s: String) -> String {
|
||||
if next_ch == "/" {
|
||||
// URL guard: prev char ':' means this is "://", not a comment.
|
||||
if prev == ":" {
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
@@ -360,7 +361,7 @@ fn strip_code_comments(s: String) -> String {
|
||||
}
|
||||
let prev = ""
|
||||
} else {
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
}
|
||||
@@ -369,23 +370,23 @@ fn strip_code_comments(s: String) -> String {
|
||||
// Open a JS string?
|
||||
if ch == "'" {
|
||||
let in_squote = true
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "\"" {
|
||||
let in_dquote = true
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "`" {
|
||||
let in_btick = true
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
let out = out + ch
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
}
|
||||
@@ -394,14 +395,14 @@ fn strip_code_comments(s: String) -> String {
|
||||
}
|
||||
}
|
||||
}
|
||||
out
|
||||
str_join(out_parts, "")
|
||||
}
|
||||
|
||||
// scan_string — scan a quoted string literal, handling \" escapes.
|
||||
// Starts AFTER the opening quote. Returns { "text": content, "pos": i_after_close }
|
||||
fn scan_string(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
let i = start
|
||||
let text = ""
|
||||
let parts: [String] = native_list_empty()
|
||||
let running = true
|
||||
while running {
|
||||
if i >= total {
|
||||
@@ -414,26 +415,26 @@ fn scan_string(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
if next_i < total {
|
||||
let next_ch: String = native_list_get(chars, next_i)
|
||||
if next_ch == "\"" {
|
||||
let text = text + "\""
|
||||
let parts = native_list_append(parts, "\"")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "n" {
|
||||
let text = text + "\n"
|
||||
let parts = native_list_append(parts, "\n")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "t" {
|
||||
let text = text + "\t"
|
||||
let parts = native_list_append(parts, "\t")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "r" {
|
||||
let text = text + "\r"
|
||||
let parts = native_list_append(parts, "\r")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "\\" {
|
||||
let text = text + "\\"
|
||||
let parts = native_list_append(parts, "\\")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
let text = text + next_ch
|
||||
let parts = native_list_append(parts, next_ch)
|
||||
let i = next_i + 1
|
||||
}
|
||||
}
|
||||
@@ -448,13 +449,13 @@ fn scan_string(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
let i = i + 1
|
||||
let running = false
|
||||
} else {
|
||||
let text = text + ch
|
||||
let parts = native_list_append(parts, ch)
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
{ "text": text, "pos": i }
|
||||
{ "text": str_join(parts, ""), "pos": i }
|
||||
}
|
||||
|
||||
// ── Main lexer ────────────────────────────────────────────────────────────────
|
||||
|
||||
@@ -687,6 +687,29 @@ fn parse_stmt(tokens: [Map<String, Any>], pos: Int) -> Map<String, Any> {
|
||||
return make_result({ "stmt": "Return", "value": val }, p)
|
||||
}
|
||||
|
||||
// extern fn declaration (no body — forward declaration for separate compilation)
|
||||
if k == "Extern" {
|
||||
let p = pos + 1
|
||||
let k2: String = tok_kind(tokens, p)
|
||||
if str_eq(k2, "Fn") {
|
||||
let p = p + 1
|
||||
let name: String = tok_value(tokens, p)
|
||||
let p = p + 1
|
||||
let r = parse_params(tokens, p)
|
||||
let params = r["params"]
|
||||
let p = r["pos"]
|
||||
let ret_type = ""
|
||||
let k3: String = tok_kind(tokens, p)
|
||||
if str_eq(k3, "Arrow") {
|
||||
let p = p + 1
|
||||
let kt: String = tok_kind(tokens, p)
|
||||
if str_eq(kt, "Ident") { let ret_type = tok_value(tokens, p) }
|
||||
let p = skip_type(tokens, p)
|
||||
}
|
||||
return make_result({ "stmt": "ExternFn", "name": name, "params": params, "ret_type": ret_type }, p)
|
||||
}
|
||||
}
|
||||
|
||||
// fn definition
|
||||
if k == "Fn" {
|
||||
let p = pos + 1
|
||||
|
||||
@@ -0,0 +1,379 @@
|
||||
// elb.el - El Build Coordinator
|
||||
//
|
||||
// The build system for El programs. Written in El. Builds El.
|
||||
//
|
||||
// Usage:
|
||||
// elb # build from manifest.el in current dir
|
||||
// elb --clean # remove generated artifacts and rebuild
|
||||
// elb --dry-run # print actions without executing
|
||||
// elb --jobs=N # parallel compile jobs (default: 4)
|
||||
// elb --out=DIR # output directory (default: dist)
|
||||
// elb --runtime=PATH # path to el_runtime.c
|
||||
//
|
||||
// How it works (the .NET model):
|
||||
// 1. Read manifest.el to find the entry file
|
||||
// 2. Walk the import graph depth-first, build topological order
|
||||
// 3. For each file: if .el is newer than .elh/.c, compile with elc --emit-header
|
||||
// 4. Link all .c files + el_runtime.c into the final binary
|
||||
//
|
||||
// Each module compiles independently - no 128K-line blobs.
|
||||
// Downstream compilations read .elh headers (function signatures only),
|
||||
// not source. Incremental: only recompile what changed.
|
||||
|
||||
// -- Flags ---------------------------------------------------------------------
|
||||
|
||||
fn flag_bool(argv: [String], name: String) -> Bool {
|
||||
let n: Int = native_list_len(argv)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let a: String = native_list_get(argv, i)
|
||||
if str_eq(a, name) { return true }
|
||||
let i = i + 1
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
fn flag_val(argv: [String], name: String, default_val: String) -> String {
|
||||
let n: Int = native_list_len(argv)
|
||||
let prefix: String = name + "="
|
||||
let i = 0
|
||||
while i < n {
|
||||
let a: String = native_list_get(argv, i)
|
||||
if str_starts_with(a, prefix) {
|
||||
return str_slice(a, str_len(prefix), str_len(a))
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return default_val
|
||||
}
|
||||
|
||||
// -- Manifest parsing ----------------------------------------------------------
|
||||
//
|
||||
// Read the entry file from manifest.el:
|
||||
// build { entry "soul.el" }
|
||||
|
||||
fn parse_manifest_entry(src: String) -> String {
|
||||
let lines: [String] = str_split(src, "\n")
|
||||
let n: Int = native_list_len(lines)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let line: String = native_list_get(lines, i)
|
||||
let t: String = str_trim(line)
|
||||
if str_starts_with(t, "entry ") {
|
||||
// entry "soul.el"
|
||||
let after: String = str_slice(t, 6, str_len(t))
|
||||
let trimmed: String = str_trim(after)
|
||||
// strip surrounding quotes
|
||||
if str_starts_with(trimmed, "\"") {
|
||||
let inner: String = str_slice(trimmed, 1, str_len(trimmed))
|
||||
let q: Int = str_index_of(inner, "\"")
|
||||
if q >= 0 {
|
||||
return str_slice(inner, 0, q)
|
||||
}
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
fn parse_manifest_name(src: String) -> String {
|
||||
let lines: [String] = str_split(src, "\n")
|
||||
let n: Int = native_list_len(lines)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let line: String = native_list_get(lines, i)
|
||||
let t: String = str_trim(line)
|
||||
if str_starts_with(t, "package ") {
|
||||
let after: String = str_slice(t, 8, str_len(t))
|
||||
let trimmed: String = str_trim(after)
|
||||
if str_starts_with(trimmed, "\"") {
|
||||
let inner: String = str_slice(trimmed, 1, str_len(trimmed))
|
||||
let q: Int = str_index_of(inner, "\"")
|
||||
if q >= 0 {
|
||||
return str_slice(inner, 0, q)
|
||||
}
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return "out"
|
||||
}
|
||||
|
||||
// -- Path helpers ---------------------------------------------------------------
|
||||
|
||||
fn dirname_of(path: String) -> String {
|
||||
let n: Int = str_len(path)
|
||||
let i: Int = n - 1
|
||||
while i >= 0 {
|
||||
let c: String = str_slice(path, i, i + 1)
|
||||
if str_eq(c, "/") {
|
||||
return str_slice(path, 0, i)
|
||||
}
|
||||
let i = i - 1
|
||||
}
|
||||
return "."
|
||||
}
|
||||
|
||||
fn basename_noext(path: String) -> String {
|
||||
// strip directory
|
||||
let n: Int = str_len(path)
|
||||
let last_slash: Int = -1
|
||||
let i = 0
|
||||
while i < n {
|
||||
let c: String = str_slice(path, i, i + 1)
|
||||
if str_eq(c, "/") { let last_slash = i }
|
||||
let i = i + 1
|
||||
}
|
||||
let base: String = str_slice(path, last_slash + 1, n)
|
||||
// strip .el extension
|
||||
let bn: Int = str_len(base)
|
||||
if str_ends_with(base, ".el") {
|
||||
return str_slice(base, 0, bn - 3)
|
||||
}
|
||||
return base
|
||||
}
|
||||
|
||||
fn path_with_ext(path: String, ext: String) -> String {
|
||||
let n: Int = str_len(path)
|
||||
if str_ends_with(path, ".el") {
|
||||
return str_slice(path, 0, n - 3) + ext
|
||||
}
|
||||
return path + ext
|
||||
}
|
||||
|
||||
fn file_is_newer(a: String, b: String) -> Bool {
|
||||
// Returns true if file a is newer than file b, or if b doesn't exist.
|
||||
// Uses exec_capture with stat to compare modification times.
|
||||
let cmd: String = "test -f " + b + " && test " + a + " -nt " + b + " && echo yes || echo no"
|
||||
let result: String = str_trim(exec_capture(cmd))
|
||||
if str_eq(result, "yes") { return true }
|
||||
// b doesn't exist - check with test -f
|
||||
let exist_cmd: String = "test -f " + b + " && echo exists || echo missing"
|
||||
let exist: String = str_trim(exec_capture(exist_cmd))
|
||||
if str_eq(exist, "missing") { return true }
|
||||
return false
|
||||
}
|
||||
|
||||
// -- Import graph walker --------------------------------------------------------
|
||||
//
|
||||
// Walk import statements in each .el file to build the dependency graph.
|
||||
// Returns a list of absolute paths in topological order (deps before dependents).
|
||||
|
||||
fn parse_import_path(line: String, dir: String) -> String {
|
||||
let t: String = str_trim(line)
|
||||
if str_starts_with(t, "import \"") {
|
||||
let after: String = str_slice(t, 8, str_len(t))
|
||||
let q: Int = str_index_of(after, "\"")
|
||||
if q > 0 {
|
||||
let mod: String = str_slice(after, 0, q)
|
||||
return dir + "/" + mod
|
||||
}
|
||||
}
|
||||
if str_starts_with(t, "from ") {
|
||||
let after: String = str_slice(t, 5, str_len(t))
|
||||
let sp: Int = str_index_of(after, " ")
|
||||
if sp > 0 {
|
||||
let mod: String = str_trim(str_slice(after, 0, sp))
|
||||
if !str_eq(mod, "") {
|
||||
return dir + "/" + mod + ".el"
|
||||
}
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
fn walk_imports(src_path: String, visited: [String], order: [String]) -> Map<String, Any> {
|
||||
// Dedup check
|
||||
let n: Int = native_list_len(visited)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let v: String = native_list_get(visited, i)
|
||||
if str_eq(v, src_path) {
|
||||
return { "visited": visited, "order": order }
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
let visited = native_list_append(visited, src_path)
|
||||
|
||||
let source: String = fs_read(src_path)
|
||||
if str_eq(source, "") {
|
||||
return { "visited": visited, "order": order }
|
||||
}
|
||||
let dir: String = dirname_of(src_path)
|
||||
let lines: [String] = str_split(source, "\n")
|
||||
let ln: Int = native_list_len(lines)
|
||||
let j = 0
|
||||
while j < ln {
|
||||
let line: String = native_list_get(lines, j)
|
||||
let imp: String = parse_import_path(line, dir)
|
||||
if !str_eq(imp, "") {
|
||||
let r = walk_imports(imp, visited, order)
|
||||
let visited = r["visited"]
|
||||
let order = r["order"]
|
||||
}
|
||||
let j = j + 1
|
||||
}
|
||||
// Add self after all deps
|
||||
let order = native_list_append(order, src_path)
|
||||
return { "visited": visited, "order": order }
|
||||
}
|
||||
|
||||
// -- Build ----------------------------------------------------------------------
|
||||
|
||||
fn compile_module(src_path: String, out_dir: String, elc_bin: String, dry_run: Bool, verbose: Bool) -> Bool {
|
||||
let bname: String = basename_noext(src_path)
|
||||
let c_out: String = out_dir + "/" + bname + ".c"
|
||||
let elh_out: String = out_dir + "/" + bname + ".elh"
|
||||
|
||||
// Check if recompile needed
|
||||
if !file_is_newer(src_path, c_out) {
|
||||
if verbose {
|
||||
println(" skip " + bname + ".el (up to date)")
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// elc streams C to stdout (collect mode not yet implemented); use
|
||||
// shell redirection so the output lands in the file, not the terminal.
|
||||
let cmd: String = elc_bin + " --emit-header " + src_path + " > " + c_out + " 2>&1"
|
||||
println(" compile " + src_path)
|
||||
|
||||
if dry_run { return true }
|
||||
|
||||
let ret: Int = exec_command(cmd)
|
||||
if ret != 0 {
|
||||
println("elb: compile failed: " + src_path)
|
||||
return false
|
||||
}
|
||||
|
||||
// Move the generated .elh (written next to the source by elc) into
|
||||
// out_dir so that #include "module.elh" lines in the generated .c
|
||||
// files resolve correctly when cc is invoked with -I <out_dir>.
|
||||
let src_elh: String = path_with_ext(src_path, ".elh")
|
||||
let mv_cmd: String = "cp " + src_elh + " " + elh_out + " 2>/dev/null || true"
|
||||
exec_command(mv_cmd)
|
||||
|
||||
return true
|
||||
}
|
||||
|
||||
fn link_binary(c_files: [String], out_bin: String, runtime_path: String, out_dir: String, dry_run: Bool) -> Bool {
|
||||
let n: Int = native_list_len(c_files)
|
||||
let parts: [String] = native_list_empty()
|
||||
// Include both the runtime dir (for el_runtime.h) and the output dir
|
||||
// (for module.elh cross-module forward declarations).
|
||||
let parts = native_list_append(parts, "cc -O2 -I " + dirname_of(runtime_path) + " -I " + out_dir)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let f: String = native_list_get(c_files, i)
|
||||
let parts = native_list_append(parts, f)
|
||||
let i = i + 1
|
||||
}
|
||||
let parts = native_list_append(parts, runtime_path)
|
||||
let parts = native_list_append(parts, "-lcurl -lpthread")
|
||||
let parts = native_list_append(parts, "-o " + out_bin)
|
||||
let cmd: String = str_join(parts, " ")
|
||||
println(" link " + out_bin)
|
||||
if dry_run { return true }
|
||||
let ret: Int = exec_command(cmd)
|
||||
if ret != 0 {
|
||||
println("elb: link failed")
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
// -- Main -----------------------------------------------------------------------
|
||||
|
||||
fn main() -> Void {
|
||||
let argv: [String] = args()
|
||||
let clean: Bool = flag_bool(argv, "--clean")
|
||||
let dry_run: Bool = flag_bool(argv, "--dry-run")
|
||||
let verbose: Bool = flag_bool(argv, "--verbose")
|
||||
let out_dir: String = flag_val(argv, "--out", "dist")
|
||||
let elc_bin: String = flag_val(argv, "--elc", "elc")
|
||||
let runtime: String = flag_val(argv, "--runtime", "")
|
||||
|
||||
// Find manifest
|
||||
let manifest_src: String = fs_read("manifest.el")
|
||||
if str_eq(manifest_src, "") {
|
||||
println("elb: no manifest.el found in current directory")
|
||||
exit(1)
|
||||
}
|
||||
|
||||
let pkg_name: String = parse_manifest_name(manifest_src)
|
||||
let entry: String = parse_manifest_entry(manifest_src)
|
||||
if str_eq(entry, "") {
|
||||
println("elb: manifest.el has no 'entry' declaration")
|
||||
exit(1)
|
||||
}
|
||||
|
||||
println("elb: building " + pkg_name + " (entry: " + entry + ")")
|
||||
|
||||
// Locate runtime
|
||||
let runtime_path: String = runtime
|
||||
if str_eq(runtime_path, "") {
|
||||
// Try to find el_runtime.c relative to elc binary
|
||||
let which_out: String = str_trim(exec_capture("which " + elc_bin + " 2>/dev/null"))
|
||||
if !str_eq(which_out, "") {
|
||||
let elc_dir: String = dirname_of(which_out)
|
||||
runtime_path = elc_dir + "/../el-compiler/runtime/el_runtime.c"
|
||||
}
|
||||
}
|
||||
if str_eq(runtime_path, "") {
|
||||
println("elb: cannot locate el_runtime.c - use --runtime=PATH")
|
||||
exit(1)
|
||||
}
|
||||
|
||||
// Ensure output directory
|
||||
let mkdir_ret: Int = exec_command("mkdir -p " + out_dir)
|
||||
|
||||
// Clean if requested
|
||||
if clean {
|
||||
println("elb: cleaning " + out_dir)
|
||||
if !dry_run {
|
||||
let rm_ret: Int = exec_command("rm -f " + out_dir + "/*.c " + out_dir + "/*.elh")
|
||||
}
|
||||
}
|
||||
|
||||
// Walk import graph from entry file
|
||||
let empty_visited: [String] = native_list_empty()
|
||||
let empty_order: [String] = native_list_empty()
|
||||
let r = walk_imports(entry, empty_visited, empty_order)
|
||||
let order: [String] = r["order"]
|
||||
let total: Int = native_list_len(order)
|
||||
println("elb: " + native_int_to_str(total) + " modules in build graph")
|
||||
|
||||
// Compile each module
|
||||
let c_files: [String] = native_list_empty()
|
||||
let i = 0
|
||||
let ok = true
|
||||
while i < total {
|
||||
let src: String = native_list_get(order, i)
|
||||
let bname: String = basename_noext(src)
|
||||
let c_out: String = out_dir + "/" + bname + ".c"
|
||||
let compiled: Bool = compile_module(src, out_dir, elc_bin, dry_run, verbose)
|
||||
if !compiled {
|
||||
let ok = false
|
||||
let i = total
|
||||
} else {
|
||||
let c_files = native_list_append(c_files, c_out)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
if !ok {
|
||||
println("elb: build failed")
|
||||
exit(1)
|
||||
}
|
||||
|
||||
// Link
|
||||
let out_bin: String = out_dir + "/" + pkg_name
|
||||
let linked: Bool = link_binary(c_files, out_bin, runtime_path, out_dir, dry_run)
|
||||
if !linked {
|
||||
println("elb: link failed")
|
||||
exit(1)
|
||||
}
|
||||
|
||||
println("elb: done -> " + out_bin)
|
||||
}
|
||||
+1270
-20
File diff suppressed because it is too large
Load Diff
+80
@@ -0,0 +1,80 @@
|
||||
#!/usr/bin/env bash
|
||||
# install.sh — Install the El SDK from the latest Gitea release.
|
||||
#
|
||||
# Usage:
|
||||
# bash install.sh
|
||||
# EL_VERSION=v1.0.0 bash install.sh # pin a specific release tag
|
||||
# EL_PREFIX=/opt/el bash install.sh # custom install prefix
|
||||
#
|
||||
# Environment variables:
|
||||
# EL_VERSION Release tag to download (default: latest)
|
||||
# EL_PREFIX Install prefix (default: /usr/local)
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
REPO_BASE="https://git.neuralplatform.ai/neuron-technologies/el"
|
||||
VERSION="${EL_VERSION:-latest}"
|
||||
PREFIX="${EL_PREFIX:-/usr/local}"
|
||||
|
||||
BIN_DIR="${PREFIX}/bin"
|
||||
LIB_DIR="${PREFIX}/lib/el"
|
||||
|
||||
RELEASE_BASE="${REPO_BASE}/releases/download/${VERSION}"
|
||||
|
||||
echo "==> Installing El SDK ${VERSION}"
|
||||
echo " prefix : ${PREFIX}"
|
||||
echo " bin : ${BIN_DIR}"
|
||||
echo " lib : ${LIB_DIR}"
|
||||
echo
|
||||
|
||||
# Create directories
|
||||
mkdir -p "${BIN_DIR}" "${LIB_DIR}"
|
||||
|
||||
# Download helper
|
||||
download() {
|
||||
local url="$1"
|
||||
local dest="$2"
|
||||
echo " Downloading $(basename "${dest}")..."
|
||||
if command -v curl >/dev/null 2>&1; then
|
||||
curl -fsSL "${url}" -o "${dest}"
|
||||
elif command -v wget >/dev/null 2>&1; then
|
||||
wget -q "${url}" -O "${dest}"
|
||||
else
|
||||
echo "Error: neither curl nor wget found" >&2
|
||||
exit 1
|
||||
fi
|
||||
}
|
||||
|
||||
# Download assets
|
||||
TMP_DIR="$(mktemp -d)"
|
||||
trap 'rm -rf "${TMP_DIR}"' EXIT
|
||||
|
||||
download "${RELEASE_BASE}/elc" "${TMP_DIR}/elc"
|
||||
download "${RELEASE_BASE}/el_runtime.c" "${TMP_DIR}/el_runtime.c"
|
||||
download "${RELEASE_BASE}/el_runtime.h" "${TMP_DIR}/el_runtime.h"
|
||||
|
||||
# Install
|
||||
install -m 755 "${TMP_DIR}/elc" "${BIN_DIR}/elc"
|
||||
install -m 644 "${TMP_DIR}/el_runtime.c" "${LIB_DIR}/el_runtime.c"
|
||||
install -m 644 "${TMP_DIR}/el_runtime.h" "${LIB_DIR}/el_runtime.h"
|
||||
|
||||
echo
|
||||
echo "==> El SDK installed successfully"
|
||||
echo
|
||||
echo " elc binary : ${BIN_DIR}/elc"
|
||||
echo " runtime : ${LIB_DIR}/el_runtime.c"
|
||||
echo " header : ${LIB_DIR}/el_runtime.h"
|
||||
echo
|
||||
echo "Add the following to your Makefile to build El programs:"
|
||||
echo
|
||||
echo " EL_LIB := ${LIB_DIR}"
|
||||
echo " ELC := elc"
|
||||
echo " CC := cc"
|
||||
echo " CFLAGS := -std=c11 -O2 -I\$(EL_LIB)"
|
||||
echo
|
||||
echo " dist/myapp.c: src/myapp.el"
|
||||
echo " \t\$(ELC) src/myapp.el > dist/myapp.c"
|
||||
echo
|
||||
echo " dist/myapp: dist/myapp.c"
|
||||
echo " \t\$(CC) \$(CFLAGS) -o dist/myapp dist/myapp.c \$(EL_LIB)/el_runtime.c -lcurl -lpthread"
|
||||
echo
|
||||
@@ -0,0 +1,28 @@
|
||||
# El Compiler Release v1.0.0 — 2026-05-02
|
||||
|
||||
## Components
|
||||
- `bootstrap.py` — El language compiler (Python, recursive descent parser, emits C)
|
||||
- `el_runtime.c` — El runtime (C, HTTP server, engram, DHARMA, LLM chain)
|
||||
- `el_runtime.h` — Runtime public API header
|
||||
|
||||
## Changes in this release
|
||||
|
||||
### Critical bug fixes
|
||||
- `state_set`/`state_get` are now thread-safe (pthread_mutex). Was racing across 64 worker threads.
|
||||
- `looks_like_string` threshold raised from 1,000,000 to 4GB. Unix timestamps were being dereferenced as heap pointers.
|
||||
- `fs_read` guards against negative `ftell` result (pipe/special file overflow).
|
||||
|
||||
### Engram architecture (major)
|
||||
- Two-layer activation: `background_activation` (Layer 1, broad fan-out) + `working_memory_weight` (Layer 2, executive filter)
|
||||
- Inhibitory edges: `EngramEdge.inhibitory` flag suppresses working memory promotion without affecting background activation
|
||||
- Suppression memory: `suppression_count` — nodes activated-but-suppressed accumulate pressure toward breakthrough
|
||||
- Temporal decay: `temporal_decay_rate`, `created_at`, `last_activated_at`, `activation_count` on EngramNode
|
||||
- Per-type activation thresholds (Safety: 0.05, Canonical: 0.15, Lesson: 0.25, Note: 0.40)
|
||||
- Temporal range query: `engram_query_range(start_ms, end_ms)`
|
||||
- Layered consciousness: `EngramLayer` struct, `layer_id` on nodes and edges, `EngramStore.layers[]`
|
||||
- Layer 0 override pass: safety layer fires last and cannot be suppressed
|
||||
|
||||
## SHA256
|
||||
bootstrap.py
|
||||
el_runtime.c
|
||||
el_runtime.h
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,507 @@
|
||||
/*
|
||||
* el_runtime.h — El language C runtime header
|
||||
*
|
||||
* Declares all built-in functions available to compiled El programs.
|
||||
* Include this in every generated .c file.
|
||||
*
|
||||
* Value model:
|
||||
* All El values are represented as el_val_t (= int64_t).
|
||||
* On 64-bit systems a pointer fits in int64_t.
|
||||
* String values are cast: (el_val_t)(uintptr_t)"hello"
|
||||
* Integer values are stored directly.
|
||||
* This lets arithmetic work naturally while still passing strings around.
|
||||
*
|
||||
* Type conventions (El -> C):
|
||||
* String -> el_val_t (holds const char* via uintptr_t cast)
|
||||
* Int -> el_val_t
|
||||
* Bool -> el_val_t (0 = false, nonzero = true)
|
||||
* Any -> el_val_t
|
||||
* Void -> void
|
||||
*
|
||||
* Macros for convenience:
|
||||
* EL_STR(s) cast string literal to el_val_t
|
||||
* EL_CSTR(v) cast el_val_t back to const char*
|
||||
* EL_INT(v) identity — el_val_t is already int64_t
|
||||
*
|
||||
* Link requirements:
|
||||
* -lcurl — required for the HTTP client (http_get, http_post, llm_*).
|
||||
* -lpthread — required for the HTTP server (one detached thread per
|
||||
* connection, capped at 64 concurrent).
|
||||
* -loqs — optional; required only when liboqs is installed and the
|
||||
* pq_* / sha3_256_hex entry points are needed. Detected at
|
||||
* compile time via __has_include(<oqs/oqs.h>).
|
||||
* -lcrypto — optional; pulled in alongside -loqs. Used for X25519 in
|
||||
* pq_hybrid_* and HKDF-SHA256 derivation.
|
||||
*
|
||||
* Canonical compile command:
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
*
|
||||
* With liboqs (post-quantum stack):
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread -loqs -lcrypto \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
*/
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <stdint.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
typedef int64_t el_val_t;
|
||||
|
||||
#define EL_STR(s) ((el_val_t)(uintptr_t)(s))
|
||||
#define EL_CSTR(v) ((const char*)(uintptr_t)(v))
|
||||
#define EL_INT(v) (v)
|
||||
#define EL_NULL ((el_val_t)0)
|
||||
|
||||
/* Float values share the el_val_t (int64) slot via a bit-cast.
|
||||
* The codegen emits Float literals as `el_from_float(<dbl>)` so the
|
||||
* underlying bits represent the IEEE 754 double. Float-aware builtins
|
||||
* (math, format, json) round-trip via these helpers. */
|
||||
static inline double el_to_float(el_val_t v) {
|
||||
union { int64_t i; double f; } u;
|
||||
u.i = (int64_t)v;
|
||||
return u.f;
|
||||
}
|
||||
|
||||
static inline el_val_t el_from_float(double f) {
|
||||
union { double f; int64_t i; } u;
|
||||
u.f = f;
|
||||
return (el_val_t)u.i;
|
||||
}
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* ── I/O ──────────────────────────────────────────────────────────────────── */
|
||||
|
||||
void println(el_val_t s);
|
||||
void print(el_val_t s);
|
||||
el_val_t readline(void);
|
||||
|
||||
/* ── String builtins ─────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_str_concat(el_val_t a, el_val_t b);
|
||||
el_val_t str_eq(el_val_t a, el_val_t b);
|
||||
el_val_t str_starts_with(el_val_t s, el_val_t prefix);
|
||||
el_val_t str_ends_with(el_val_t s, el_val_t suffix);
|
||||
el_val_t str_len(el_val_t s);
|
||||
el_val_t str_concat(el_val_t a, el_val_t b);
|
||||
el_val_t int_to_str(el_val_t n);
|
||||
el_val_t str_to_int(el_val_t s);
|
||||
el_val_t str_slice(el_val_t s, el_val_t start, el_val_t end);
|
||||
el_val_t str_contains(el_val_t s, el_val_t sub);
|
||||
el_val_t str_replace(el_val_t s, el_val_t from, el_val_t to);
|
||||
el_val_t str_to_upper(el_val_t s);
|
||||
el_val_t str_to_lower(el_val_t s);
|
||||
el_val_t str_trim(el_val_t s);
|
||||
|
||||
/* ── Math ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_abs(el_val_t n);
|
||||
el_val_t el_max(el_val_t a, el_val_t b);
|
||||
el_val_t el_min(el_val_t a, el_val_t b);
|
||||
|
||||
/* ── Refcount (ARC) ──────────────────────────────────────────────────────────
|
||||
* Lists and Maps carry a refcount. Strings and ints do not — el_retain and
|
||||
* el_release are safe no-ops on non-refcounted values (they sniff a magic
|
||||
* header at offset 0 and only act if the magic matches).
|
||||
*
|
||||
* Codegen emits these at let-binding shadowing, function entry (params), and
|
||||
* function exit (locals other than the returned value). The refcount lets
|
||||
* el_list_append and el_map_set mutate in place when uniquely owned (cheap)
|
||||
* and copy-on-write when shared (preserves persistent semantics across
|
||||
* accumulator patterns in the compiler itself). */
|
||||
|
||||
void el_retain(el_val_t v);
|
||||
void el_release(el_val_t v);
|
||||
|
||||
/* ── List ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_list_new(el_val_t count, ...);
|
||||
el_val_t el_list_len(el_val_t list);
|
||||
el_val_t el_list_get(el_val_t list, el_val_t index);
|
||||
el_val_t el_list_append(el_val_t list, el_val_t elem);
|
||||
el_val_t el_list_empty(void);
|
||||
el_val_t el_list_clone(el_val_t list);
|
||||
|
||||
/* ── Map ─────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_map_new(el_val_t pair_count, ...);
|
||||
el_val_t el_get_field(el_val_t map, el_val_t key);
|
||||
el_val_t el_map_get(el_val_t map, el_val_t key);
|
||||
el_val_t el_map_set(el_val_t map, el_val_t key, el_val_t value);
|
||||
|
||||
/* ── HTTP ─────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t http_get(el_val_t url);
|
||||
el_val_t http_post(el_val_t url, el_val_t body);
|
||||
el_val_t http_post_json(el_val_t url, el_val_t json_body);
|
||||
el_val_t http_get_with_headers(el_val_t url, el_val_t headers_map);
|
||||
el_val_t http_post_with_headers(el_val_t url, el_val_t body, el_val_t headers_map);
|
||||
el_val_t http_post_form_auth(el_val_t url, el_val_t form_body, el_val_t auth_header);
|
||||
el_val_t http_delete(el_val_t url);
|
||||
void http_serve(el_val_t port, el_val_t handler);
|
||||
void http_set_handler(el_val_t name);
|
||||
|
||||
/* HTTP server v2 ─────────────────────────────────────────────────────────────
|
||||
* Same dispatch model as http_serve, but the handler signature is widened:
|
||||
*
|
||||
* el_val_t handler(method, path, headers_map, body)
|
||||
*
|
||||
* `headers_map` is an ElMap from lowercased header name → header value (both
|
||||
* Strings). Repeated headers are joined with ", " per RFC 7230.
|
||||
*
|
||||
* Response value: the handler may return either
|
||||
* (a) a plain body string — same auto-content-type / 200-OK behaviour as
|
||||
* http_serve (3-arg) — or
|
||||
* (b) a response envelope built with `http_response(status, headers_json,
|
||||
* body)`. The runtime detects the envelope discriminator
|
||||
* `"el_http_response":1` at the start of the returned string and
|
||||
* unpacks status / headers / body before sending.
|
||||
*
|
||||
* The 3-arg http_serve(port, handler) remains supported unchanged for
|
||||
* existing handlers (e.g. products/web/server.el): it dispatches with
|
||||
* (method, path, body), hardcodes 200 OK, and auto-detects content type. */
|
||||
void http_serve_v2(el_val_t port, el_val_t handler);
|
||||
void http_set_handler_v2(el_val_t name);
|
||||
|
||||
/* Build an HTTP response envelope. `headers_json` should be a JSON object
|
||||
* literal like `{"WWW-Authenticate":"Basic"}` (or "" / "{}" for none). The
|
||||
* returned string carries the discriminator `{"el_http_response":1,...}`
|
||||
* which the runtime's send-path detects and unpacks. Detection happens
|
||||
* uniformly inside http_send_response, so a 3-arg handler may also return
|
||||
* an envelope. The 3-arg variant remains documented as a fixed 200-OK
|
||||
* auto-content-type contract for legacy handlers that return plain bodies. */
|
||||
el_val_t http_response(el_val_t status, el_val_t headers_json, el_val_t body);
|
||||
|
||||
/* HTTP timeout — every libcurl request honors EL_HTTP_TIMEOUT_MS (default
|
||||
* 60000ms). Read lazily on first use, so setting the env var any time before
|
||||
* the first http_* call is sufficient. */
|
||||
|
||||
/* Streaming variants — write the response body straight to a file via
|
||||
* libcurl's CURLOPT_WRITEFUNCTION = fwrite. These bypass the el_val_t string
|
||||
* wrapper entirely, so binary payloads (audio/mpeg, image/png, etc.) survive
|
||||
* embedded NUL bytes that would truncate a strlen()-based code path.
|
||||
*
|
||||
* Both honor EL_HTTP_TIMEOUT_MS, follow redirects, and accept the same
|
||||
* `headers_map` shape as http_post_with_headers (ElMap of String→String).
|
||||
*
|
||||
* Return value: 1 on success (file fully written), 0 on any failure
|
||||
* (network, file open, partial write). On failure the output file is removed
|
||||
* so callers cannot mistake a partially-written file for a valid one. */
|
||||
el_val_t http_post_to_file(el_val_t url, el_val_t body, el_val_t headers_map, el_val_t output_path);
|
||||
el_val_t http_get_to_file(el_val_t url, el_val_t headers_map, el_val_t output_path);
|
||||
|
||||
/* ── URL encoding ────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t url_encode(el_val_t s); /* RFC 3986 unreserved set */
|
||||
el_val_t url_decode(el_val_t s); /* '+' → space, %XX → byte */
|
||||
|
||||
/* ── Filesystem ──────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t fs_read(el_val_t path);
|
||||
el_val_t fs_write(el_val_t path, el_val_t content);
|
||||
el_val_t fs_list(el_val_t path);
|
||||
el_val_t fs_exists(el_val_t path);
|
||||
el_val_t fs_mkdir(el_val_t path); /* mkdir -p, mode 0755 */
|
||||
|
||||
/* Length-explicit binary write. `length` is an Int (el_val_t holding the
|
||||
* byte count). The caller knows the length from context — typically because
|
||||
* `bytes` came from base64_decode (which produces a magic-tagged binary
|
||||
* buffer with embedded NULs possible) and the caller already tracks the
|
||||
* decoded length, OR because the bytes came from a fixed-size source
|
||||
* (sha256_bytes = 32, hmac_sha256_bytes = 32). Bypasses strlen entirely.
|
||||
*
|
||||
* Returns 1 on success, 0 on failure (invalid path, can't open, partial
|
||||
* write, negative length). On partial-write failure, the file is removed
|
||||
* so callers cannot read back a truncated artefact. */
|
||||
el_val_t fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t length);
|
||||
|
||||
/* ── JSON ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t json_get(el_val_t json, el_val_t key);
|
||||
el_val_t json_parse(el_val_t s);
|
||||
el_val_t json_stringify(el_val_t v);
|
||||
el_val_t json_get_string(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_int(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_float(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_bool(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_raw(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_set(el_val_t json_str, el_val_t key, el_val_t value);
|
||||
el_val_t json_array_len(el_val_t json_str);
|
||||
el_val_t json_array_get(el_val_t json_str, el_val_t index);
|
||||
el_val_t json_array_get_string(el_val_t json_str, el_val_t index);
|
||||
|
||||
/* ── Time ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t time_now(void);
|
||||
el_val_t time_now_utc(void);
|
||||
el_val_t sleep_secs(el_val_t secs);
|
||||
el_val_t sleep_ms(el_val_t ms);
|
||||
el_val_t time_format(el_val_t ts, el_val_t fmt);
|
||||
el_val_t time_to_parts(el_val_t ts);
|
||||
el_val_t time_from_parts(el_val_t secs, el_val_t ns, el_val_t tz);
|
||||
el_val_t time_add(el_val_t ts, el_val_t n, el_val_t unit);
|
||||
el_val_t time_diff(el_val_t ts1, el_val_t ts2, el_val_t unit);
|
||||
|
||||
/* ── UUID ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t uuid_new(void);
|
||||
el_val_t uuid_v4(void);
|
||||
|
||||
/* ── Environment ─────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t env(el_val_t key);
|
||||
|
||||
/* ── In-process state K/V ────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t state_set(el_val_t key, el_val_t value);
|
||||
el_val_t state_get(el_val_t key);
|
||||
el_val_t state_del(el_val_t key);
|
||||
el_val_t state_keys(void);
|
||||
|
||||
/* ── Float formatting ────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t float_to_str(el_val_t f);
|
||||
el_val_t int_to_float(el_val_t n);
|
||||
el_val_t float_to_int(el_val_t f);
|
||||
el_val_t format_float(el_val_t f, el_val_t decimals);
|
||||
el_val_t decimal_round(el_val_t f, el_val_t decimals);
|
||||
el_val_t str_to_float(el_val_t s);
|
||||
|
||||
/* ── Math (Float-aware) ──────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t math_sqrt(el_val_t f);
|
||||
el_val_t math_log(el_val_t f);
|
||||
el_val_t math_ln(el_val_t f);
|
||||
el_val_t math_sin(el_val_t f);
|
||||
el_val_t math_cos(el_val_t f);
|
||||
el_val_t math_pi(void);
|
||||
|
||||
/* ── String additions ────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t str_index_of(el_val_t s, el_val_t sub);
|
||||
el_val_t str_split(el_val_t s, el_val_t sep);
|
||||
el_val_t str_char_at(el_val_t s, el_val_t i);
|
||||
el_val_t str_char_code(el_val_t s, el_val_t i);
|
||||
el_val_t str_pad_left(el_val_t s, el_val_t width, el_val_t pad);
|
||||
el_val_t str_pad_right(el_val_t s, el_val_t width, el_val_t pad);
|
||||
el_val_t str_format(el_val_t template, el_val_t data);
|
||||
el_val_t str_lower(el_val_t s);
|
||||
el_val_t str_upper(el_val_t s);
|
||||
|
||||
/* ── List additions ──────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t list_push(el_val_t list, el_val_t elem);
|
||||
el_val_t list_push_front(el_val_t list, el_val_t elem);
|
||||
el_val_t list_join(el_val_t list, el_val_t sep);
|
||||
el_val_t list_range(el_val_t start, el_val_t end);
|
||||
|
||||
/* ── Bool helpers ────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t bool_to_str(el_val_t b);
|
||||
|
||||
/* ── Numeric parsing ─────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t parse_int(el_val_t s, el_val_t default_val);
|
||||
|
||||
/* ── Process ─────────────────────────────────────────────────────────────── */
|
||||
|
||||
void exit_program(el_val_t code);
|
||||
el_val_t getpid_now(void);
|
||||
|
||||
/* ── CGI identity ─────────────────────────────────────────────────────────────
|
||||
* Called at the start of main() in CGI programs (those with a `cgi {}` block).
|
||||
* Records the program's DHARMA identity before any other code executes. */
|
||||
|
||||
void el_cgi_init(el_val_t name, el_val_t dharma_id, el_val_t principal,
|
||||
el_val_t network, el_val_t engram);
|
||||
|
||||
/* ── DHARMA network builtins ─────────────────────────────────────────────────
|
||||
* Available to CGI programs (declared with a `cgi {}` block).
|
||||
*
|
||||
* Peers are addressed by `dharma_id` of the form
|
||||
* "<registry-id>@<transport-url>" e.g. "ntn-genesis@http://localhost:7770"
|
||||
* If the @<url> portion is omitted, transport defaults to
|
||||
* "http://localhost:7770" (the local CGI daemon assumption).
|
||||
*
|
||||
* Wire protocol (all peers expose):
|
||||
* POST <url>/dharma/recv { channel, from, content } → response body
|
||||
* POST <url>/dharma/event { type, payload, source, timestamp }
|
||||
* POST <url>/api/activate { query } → list of nodes
|
||||
*
|
||||
* Hosting application's responsibility: an El program with a `cgi {}` block
|
||||
* runs http_serve() with its own request handler; that handler should route
|
||||
* "/dharma/event" requests by calling el_runtime_dharma_event_arrive() so
|
||||
* incoming events feed dharma_field() queues. The runtime itself does not
|
||||
* intercept any /dharma path. */
|
||||
|
||||
el_val_t dharma_connect(el_val_t cgi_id);
|
||||
el_val_t dharma_send(el_val_t channel, el_val_t content);
|
||||
el_val_t dharma_activate(el_val_t query);
|
||||
void dharma_emit(el_val_t event_type, el_val_t payload);
|
||||
el_val_t dharma_field(el_val_t event_type);
|
||||
void dharma_strengthen(el_val_t cgi_id, el_val_t weight);
|
||||
el_val_t dharma_relationship(el_val_t cgi_id);
|
||||
el_val_t dharma_peers(void);
|
||||
|
||||
/* Public C API: called by an El program's HTTP handler when a /dharma/event
|
||||
* request arrives. Pushes onto the per-event-type queue and signals any
|
||||
* pending dharma_field() blockers. All three arguments must be NUL-terminated
|
||||
* C strings (or NULL — then treated as empty). */
|
||||
void el_runtime_dharma_event_arrive(const char* event_type,
|
||||
const char* payload,
|
||||
const char* source);
|
||||
|
||||
/* ── Engram local graph primitives ───────────────────────────────────────────
|
||||
* Operate on the CGI's local Engram knowledge graph.
|
||||
* `engram_activate` queries the local graph only; `dharma_activate` is
|
||||
* network-wide across all connected CGI graphs. */
|
||||
|
||||
el_val_t engram_node(el_val_t content, el_val_t node_type, el_val_t salience);
|
||||
el_val_t engram_node_full(el_val_t content, el_val_t node_type, el_val_t label,
|
||||
el_val_t salience, el_val_t importance, el_val_t confidence,
|
||||
el_val_t tier, el_val_t tags);
|
||||
el_val_t engram_get_node(el_val_t id);
|
||||
void engram_strengthen(el_val_t node_id);
|
||||
void engram_forget(el_val_t node_id);
|
||||
el_val_t engram_node_count(void);
|
||||
el_val_t engram_search(el_val_t query, el_val_t limit);
|
||||
el_val_t engram_scan_nodes(el_val_t limit, el_val_t offset);
|
||||
void engram_connect(el_val_t from_id, el_val_t to_id, el_val_t weight, el_val_t relation);
|
||||
el_val_t engram_edge_between(el_val_t from_id, el_val_t to_id);
|
||||
el_val_t engram_neighbors(el_val_t node_id);
|
||||
el_val_t engram_neighbors_filtered(el_val_t node_id, el_val_t max_depth, el_val_t direction);
|
||||
el_val_t engram_edge_count(void);
|
||||
el_val_t engram_activate(el_val_t query, el_val_t depth);
|
||||
el_val_t engram_save(el_val_t path);
|
||||
el_val_t engram_load(el_val_t path);
|
||||
|
||||
/* JSON-string accessors — return pre-serialized JSON so HTTP handlers
|
||||
* can pass results straight through without round-tripping ElList/ElMap
|
||||
* through json_stringify. */
|
||||
el_val_t engram_get_node_json(el_val_t id);
|
||||
el_val_t engram_search_json(el_val_t query, el_val_t limit);
|
||||
el_val_t engram_scan_nodes_json(el_val_t limit, el_val_t offset);
|
||||
el_val_t engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t direction);
|
||||
el_val_t engram_activate_json(el_val_t query, el_val_t depth);
|
||||
el_val_t engram_stats_json(void);
|
||||
|
||||
/* ── LLM (Anthropic API client) ─────────────────────────────────────────────
|
||||
* All functions call https://api.anthropic.com/v1/messages with the API key
|
||||
* from env ANTHROPIC_API_KEY. Default model when empty: claude-sonnet-4-5. */
|
||||
|
||||
el_val_t llm_call(el_val_t model, el_val_t prompt);
|
||||
el_val_t llm_call_system(el_val_t model, el_val_t system_prompt, el_val_t user_prompt);
|
||||
el_val_t llm_call_agentic(el_val_t model, el_val_t system, el_val_t user, el_val_t tools);
|
||||
el_val_t llm_vision(el_val_t model, el_val_t system, el_val_t prompt, el_val_t image_url_or_b64);
|
||||
el_val_t llm_models(void);
|
||||
|
||||
/* Register a tool handler by name. The handler is looked up via dlsym
|
||||
* (mirroring http_set_handler), so any El `fn <name>(input)` compiles to
|
||||
* a global C symbol that this function can locate at runtime.
|
||||
* Handler signature: `el_val_t handler(el_val_t input_json)` — receives
|
||||
* the tool input as a JSON-string el_val_t and returns a JSON-string
|
||||
* el_val_t result. Used by llm_call_agentic. */
|
||||
void llm_register_tool(el_val_t name, el_val_t handler_fn_name);
|
||||
|
||||
/* ── args() ─────────────────────────────────────────────────────────────────
|
||||
* Provides access to command-line arguments passed to the program.
|
||||
* Populated by el_runtime_init_args() before main() runs. */
|
||||
|
||||
el_val_t args(void);
|
||||
void el_runtime_init_args(int argc, char** argv);
|
||||
|
||||
/* ── Crypto primitives ─────────────────────────────────────────────────────
|
||||
* SHA-256, HMAC-SHA-256, and base64 (standard + URL-safe).
|
||||
* Self-contained — no OpenSSL/libcrypto dependency. The implementations are
|
||||
* adapted from public-domain reference code (Brad Conte / RFC 4648).
|
||||
*
|
||||
* Bytes-returning variants (sha256_bytes, hmac_sha256_bytes) return a string
|
||||
* value whose contents are raw binary; callers usually feed these into
|
||||
* base64_encode. Note that el_val_t strings are NUL-terminated by convention,
|
||||
* so the binary payload may contain embedded NULs — pass it directly into
|
||||
* base64_encode (which uses an explicit length) rather than treating it as
|
||||
* a printable C string.
|
||||
*
|
||||
* The "base64" variants emit/accept RFC 4648 standard alphabet with padding.
|
||||
* The "base64url" variants use URL-safe alphabet (`-`/`_`) with no padding,
|
||||
* as used in JWTs. */
|
||||
|
||||
el_val_t sha256_hex(el_val_t input);
|
||||
el_val_t sha256_bytes(el_val_t input);
|
||||
el_val_t hmac_sha256_hex(el_val_t key, el_val_t message);
|
||||
el_val_t hmac_sha256_bytes(el_val_t key, el_val_t message);
|
||||
el_val_t base64_encode(el_val_t input);
|
||||
el_val_t base64_decode(el_val_t input);
|
||||
el_val_t base64url_encode(el_val_t input);
|
||||
el_val_t base64url_decode(el_val_t input);
|
||||
|
||||
/* Length-aware variants (internal — exposed for the rare caller that already
|
||||
* has a known-length binary buffer and doesn't want to round-trip through
|
||||
* a NUL-terminated el_val_t string). Sha256_bytes and hmac_sha256_bytes feed
|
||||
* these implicitly. */
|
||||
el_val_t el_sha256_bytes_n(const unsigned char* data, size_t len);
|
||||
el_val_t el_base64_encode_n(const unsigned char* data, size_t len, int url_safe);
|
||||
|
||||
/* ── Post-quantum primitives (liboqs-backed) ────────────────────────────────
|
||||
* All inputs/outputs hex-encoded. Algorithm choices:
|
||||
* Signature: CRYSTALS-Dilithium-3 (NIST level 3, balanced)
|
||||
* KEM: CRYSTALS-Kyber-768 (NIST level 3)
|
||||
* Hash: SHA3-256 (Keccak) (PQ-aware protocols favour SHA3 over SHA2)
|
||||
*
|
||||
* If liboqs is not linked (detected via __has_include(<oqs/oqs.h>) at compile
|
||||
* time), the pq_* entry points return a JSON-shaped error string so callers
|
||||
* fail loudly rather than silently fall back to classical schemes:
|
||||
* {"error":"liboqs not linked, post-quantum primitives unavailable"}
|
||||
*
|
||||
* The hybrid handshake pairs X25519 with Kyber-768 per NIST PQ guidance and
|
||||
* CNSA 2.0. Combined shared secret is HKDF-SHA256(x25519_ss || kyber_ss).
|
||||
* Even if Kyber falls, X25519 holds; if X25519 falls under quantum attack,
|
||||
* Kyber holds. SHA3-256 also remains usable independent of liboqs (the
|
||||
* Keccak permutation is PQ-OK as a primitive). */
|
||||
|
||||
el_val_t pq_keygen_signature(void);
|
||||
el_val_t pq_sign(el_val_t secret_key_hex, el_val_t message);
|
||||
el_val_t pq_verify(el_val_t public_key_hex, el_val_t message, el_val_t signature_hex);
|
||||
|
||||
el_val_t pq_kem_keygen(void);
|
||||
el_val_t pq_kem_encaps(el_val_t public_key_hex);
|
||||
el_val_t pq_kem_decaps(el_val_t secret_key_hex, el_val_t ciphertext_hex);
|
||||
|
||||
el_val_t pq_hybrid_keygen(void);
|
||||
el_val_t pq_hybrid_handshake(el_val_t remote_pub_combined);
|
||||
|
||||
el_val_t sha3_256_hex(el_val_t input);
|
||||
|
||||
/* ── Native VM builtin aliases (for compiled El source) ─────────────────────
|
||||
* These match the El VM's native_* builtins so that El source compiled
|
||||
* to C can call the same names without modification. */
|
||||
|
||||
el_val_t native_list_get(el_val_t list, el_val_t index);
|
||||
el_val_t native_list_len(el_val_t list);
|
||||
el_val_t native_list_append(el_val_t list, el_val_t elem);
|
||||
el_val_t native_list_empty(void);
|
||||
el_val_t native_list_clone(el_val_t list);
|
||||
el_val_t native_string_chars(el_val_t s);
|
||||
el_val_t native_int_to_str(el_val_t n);
|
||||
|
||||
/* ── Method-call shorthand aliases ──────────────────────────────────────────
|
||||
* The El method-call convention `obj.method(args)` compiles to
|
||||
* `method(obj, args)`. These aliases expose the runtime functions under
|
||||
* the short names that result from method calls in El source.
|
||||
*
|
||||
* Example: `myList.append(x)` → `append(myList, x)` (calls this alias)
|
||||
* `myList.len()` → `len(myList)` (calls this alias) */
|
||||
|
||||
el_val_t append(el_val_t list, el_val_t elem); /* el_list_append */
|
||||
el_val_t len(el_val_t list); /* el_list_len */
|
||||
el_val_t get(el_val_t list, el_val_t index); /* el_list_get */
|
||||
el_val_t map_get(el_val_t map, el_val_t key); /* el_map_get */
|
||||
el_val_t map_set(el_val_t map, el_val_t key, el_val_t value); /* el_map_set */
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
@@ -0,0 +1,236 @@
|
||||
# El JavaScript Backend (codegen-js)
|
||||
|
||||
**Status:** scaffolded. Hello-world compiles and runs. ~50% language coverage. Core runtime (~30 builtins) implemented. CGI / DHARMA / LLM / Engram intentionally stubbed.
|
||||
|
||||
**Authoritative files**
|
||||
|
||||
| File | Role |
|
||||
|---|---|
|
||||
| `el-compiler/src/codegen-js.el` | El → JS code generator (mirrors `codegen.el`) |
|
||||
| `el-compiler/runtime/el_runtime.js` | Browser/Node runtime that compiled programs link against |
|
||||
| `el-compiler/src/compiler.el` | Adds `compile_js()` and `--target=js` CLI dispatch |
|
||||
| `spec/codegen-js.md` | This document |
|
||||
|
||||
---
|
||||
|
||||
## 1. Why a JS backend exists
|
||||
|
||||
El compiles to C today. C is the right substrate for the agent runtime, the DHARMA daemon, and Engram. But three first-class consumers of El need to **run in a browser**, where C is not an option:
|
||||
|
||||
1. **`el-ui/runtime/`** — the activation-based frontend framework written in JS. The long-term plan is to author components and the runtime itself in El and compile them down to JS.
|
||||
2. **`cgi-studio`** — the web app for cultivating CGIs. Today it is hand-written JS. Once the JS backend is mature, the studio's UI logic can be authored in El and share types/identifier names with the CGI it cultivates.
|
||||
3. **Marketplace plugin UIs** — third parties writing browser-side El that runs untrusted in a sandbox. They need a JS target.
|
||||
|
||||
A secondary motivation: **El-on-Node**. CLI tooling, build scripts, and tests benefit from a tight `el → js → node` cycle without a `cc` step.
|
||||
|
||||
---
|
||||
|
||||
## 2. Type representation strategy
|
||||
|
||||
The C backend pretends every value is `int64_t`. That is a deliberate runtime trick to avoid dynamic dispatch in generated C. JavaScript already has tagged dynamic values, so the JS backend is **simpler**: every El value is a native JS value, and the tag of `el_val_t` collapses into the JS type system.
|
||||
|
||||
| El type | C representation | JS representation |
|
||||
|---|---|---|
|
||||
| `Int` | `int64_t` (direct) | `number` (with `Number.isSafeInteger` caveat — see §6) |
|
||||
| `Float` | `int64_t` bit-cast of `double` via `el_from_float` | `number` (no bit-cast — JS number IS a double) |
|
||||
| `Bool` | `int64_t`, 0 = false, nonzero = true | `boolean` |
|
||||
| `String` | `(int64_t)(uintptr_t)cstring` | `string` |
|
||||
| `Void` | C `void` | `undefined` |
|
||||
| `[T]` (List) | `el_val_t` pointer to refcounted struct | `Array<any>` |
|
||||
| `Map<K,V>` | `el_val_t` pointer to refcounted struct | plain object `{[key]: any}` |
|
||||
| `EL_NULL` (`0`) | `(el_val_t)0` | `null` |
|
||||
| Any | `el_val_t` | `any` (no compile-time check) |
|
||||
|
||||
**Key consequences:**
|
||||
|
||||
- `+` on two strings is JS `+` (string concat) — no `el_str_concat()` runtime call needed for the common case. The runtime DOES export `el_str_concat` for the cases where codegen does not know the types.
|
||||
- `==` on strings is `===` — not `str_eq()`. Same disambiguation logic as the C backend (look at left/right kind, fall back to `str_eq` for identifiers without int annotation).
|
||||
- `Map` access `m["foo"]` compiles to JS `m["foo"]` (no `el_get_field`). For `Field` access (`m.foo`) we emit `m["foo"]` so it works on plain objects regardless of prototype shape.
|
||||
- List access `arr[i]` is JS `arr[i]`. No bounds checking — same as C (which segfaults on bad index). Could add `el_list_get` wrapper later for safe access.
|
||||
- `EL_NULL` becomes JS `null`, not `undefined`. The runtime checks for `=== null` consistently. This avoids the JS undefined/null fork and matches El's single null value.
|
||||
|
||||
---
|
||||
|
||||
## 3. Builtin runtime layer (`el_runtime.js`)
|
||||
|
||||
Same function names as `el_runtime.c` wherever possible, so codegen-js can emit the same call sites. The runtime is a single ES module that exposes every builtin as a named export AND attaches them to a `globalThis.__el` namespace (so generated code can do either `import * as el from './el_runtime.js'` or assume globals).
|
||||
|
||||
**The codegen-js generated output uses the global-namespace style:** every emitted file starts with `import './el_runtime.js'` (which side-effects the globals) so call sites stay flat — `println(x)` not `el.println(x)`. This matches the C backend's flat call surface and keeps the generated code grep-compatible across targets.
|
||||
|
||||
### Implemented today (~30 builtins)
|
||||
|
||||
| Category | Functions |
|
||||
|---|---|
|
||||
| I/O | `println`, `print` |
|
||||
| String | `el_str_concat`, `str_concat`, `str_eq`, `str_starts_with`, `str_ends_with`, `str_len`, `int_to_str`, `str_to_int`, `str_slice`, `str_contains`, `str_replace`, `str_to_upper`, `str_to_lower`, `str_trim`, `str_index_of`, `str_split`, `str_char_at`, `str_char_code`, `str_lower`, `str_upper` |
|
||||
| Math | `el_abs`, `el_max`, `el_min` |
|
||||
| List | `el_list_new`, `el_list_len`, `el_list_get`, `el_list_append`, `el_list_empty`, `el_list_clone`, `list_push`, `list_join`, `list_range` |
|
||||
| Map | `el_map_new`, `el_get_field`, `el_map_get`, `el_map_set` |
|
||||
| HTTP | `http_get`, `http_post`, `http_post_json` (via `fetch()`, returns `Promise<string>` — see §5 async caveat) |
|
||||
| FS | `fs_read`, `fs_write`, `fs_list` (Node-only, throw in browser) |
|
||||
| JSON | `json_parse`, `json_stringify`, `json_get`, `json_get_string`, `json_get_int` |
|
||||
| Time | `time_now`, `time_now_utc`, `sleep_secs` (Node), `sleep_ms` |
|
||||
| Bool | `bool_to_str` |
|
||||
| Process | `exit_program` (Node `process.exit`, throw in browser) |
|
||||
| Refcount | `el_retain`, `el_release` (no-ops — JS has GC) |
|
||||
| ARC method-call shortforms | `append`, `len`, `get`, `map_get`, `map_set` |
|
||||
| Native VM aliases | `native_list_get`, `native_list_len`, `native_list_append`, `native_list_empty`, `native_list_clone`, `native_string_chars`, `native_int_to_str` |
|
||||
| `args` | `args()` returns `process.argv.slice(2)` in Node, `[]` in browser |
|
||||
| `state_*` | In-memory `Map` keyed by string |
|
||||
| `env` | `process.env[k]` in Node, throws in browser |
|
||||
|
||||
### Stubbed (throw at runtime)
|
||||
|
||||
Every function in this list compiles successfully but throws `Error("not supported in JS target — needs server-side delegation: <name>")` when called. This is a **runtime** error, not a compile error, so it doesn't block compilation of code that has dead-code paths through these functions.
|
||||
|
||||
- All `dharma_*` (membership in DHARMA network requires the daemon)
|
||||
- All `engram_*` (needs the embedded SQLite + activation engine — could be reimplemented in JS later)
|
||||
- All `llm_*` (CORS + API key handling — must go through a server-side proxy)
|
||||
- `http_serve` (browsers don't host servers; Node could, but that's a separate runtime mode)
|
||||
- `el_cgi_init` (CGI identity is a server-side concept)
|
||||
- Crypto: `sha256_*`, `hmac_sha256_*`, `base64*` (deferred — can use `crypto.subtle` later)
|
||||
|
||||
### Browser-side specific behavior
|
||||
|
||||
When running in a browser:
|
||||
- `println` / `print` map to `console.log` (no stdout in browsers)
|
||||
- `http_get` / `http_post` use `fetch()` (CORS applies)
|
||||
- `fs_*` throws (browsers have no fs)
|
||||
- `args()` returns `[]`
|
||||
- `env(k)` throws (or could read from a global config object — TBD)
|
||||
|
||||
When running in Node:
|
||||
- `println` / `print` map to `console.log` and `process.stdout.write`
|
||||
- `fs_*` use `node:fs/promises` (sync versions for the simple cases)
|
||||
- `args()` returns `process.argv.slice(2)`
|
||||
- `env(k)` returns `process.env[k] ?? null`
|
||||
|
||||
The runtime auto-detects via `typeof window === 'undefined'`.
|
||||
|
||||
---
|
||||
|
||||
## 4. Tradeoffs vs the C backend
|
||||
|
||||
| Concern | C backend | JS backend |
|
||||
|---|---|---|
|
||||
| **Static types** | El's `Int` becomes `int64_t`, real arithmetic | El's `Int` becomes `number` — loses precision past 2^53 |
|
||||
| **Linking model** | Static link against `el_runtime.c` + libcurl + libpthread | ES module import of `el_runtime.js` |
|
||||
| **Dynamic dispatch** | `dlsym` for `http_set_handler` / `llm_register_tool` (requires `-rdynamic`) | JS function value lookup via `globalThis[name]` — no compiler flag |
|
||||
| **Tool registry** | dlsym walks symbol table; tool fns must be top-level C symbols | Tool fns live as exports of the generated module; trivially callable |
|
||||
| **Memory model** | Refcounted lists/maps with `el_retain`/`el_release` to avoid leaks | JS GC handles all of it; `el_retain`/`el_release` are no-ops |
|
||||
| **`+` overload** | Has to dispatch in codegen between `el_str_concat` and integer `+` because at C level both are `int64_t` | JS `+` is already overloaded: `"a" + "b"` → `"ab"`, `1 + 2` → `3`. Codegen still preserves the existing dispatch for safety, but the runtime fallback is correct |
|
||||
| **Concurrency** | `pthread`-backed `http_serve` | Single-threaded event loop; `http_serve` not supported in this target |
|
||||
| **HTTP client** | libcurl, blocking, returns body string | `fetch()` is async — see §5 |
|
||||
| **CGI identity** | `el_cgi_init` runs at start of `main()` | Not supported; UI code is not a CGI principal |
|
||||
| **DHARMA / LLM** | Native, blocking, libcurl-backed | Not supported — all such calls throw and the program is expected to delegate to a server-side El daemon via plain HTTP |
|
||||
| **Compile speed** | El → C → cc → binary (cc is the slow step) | El → JS → done. Faster iteration |
|
||||
| **Output size** | Static binary ~2MB | Source `.js` + ~10kb runtime |
|
||||
|
||||
---
|
||||
|
||||
## 5. The async problem (the big deferred decision)
|
||||
|
||||
`fetch()` is async. The C backend's `http_get(url)` is synchronous and returns the body string directly. El source was written assuming sync. Three options:
|
||||
|
||||
1. **Pretend it's sync from El's POV; use synchronous XHR (browser) or `child_process.execSync('curl …')` (Node).** Bad: synchronous XHR is deprecated and frozen on the main thread; `execSync` is a hack.
|
||||
2. **Make every `http_*` builtin in the JS runtime return a `Promise`, and rewrite codegen-js to insert `await` everywhere.** This requires turning every El function that transitively calls a network builtin into an `async fn` in JS. Doable, but invasive — the El AST does not currently mark async-ness.
|
||||
3. **Compile El's call sites with implicit await; compile-time taint tracking marks every fn that transitively calls a network builtin as `async`. Generated JS uses `async function` and `await`.** This is the right answer long-term.
|
||||
|
||||
**Decision for this scaffold:** option 3, but only the runtime side is implemented. `http_get` in `el_runtime.js` returns a `Promise<string>`. `codegen-js.el` does NOT yet emit `async`/`await`. Calling `http_get` from compiled El will return a Promise that the El program will treat as a string (which produces `"[object Promise]"`). This is documented and accepted for the scaffold; the compile-time taint pass is a follow-up.
|
||||
|
||||
For now, programs that don't touch HTTP work correctly. That covers `el-ui/runtime` (which only manipulates the DOM and a graph), most of cgi-studio's pure UI components, and all hello-world style programs.
|
||||
|
||||
---
|
||||
|
||||
## 6. Number precision
|
||||
|
||||
JS `number` is IEEE 754 double — only 53 bits of integer precision. El `Int` is `int64_t` and the runtime sometimes uses the full 64 bits (e.g. `time_now_utc` returns nanoseconds-since-epoch, which exceeds 2^53 in practice).
|
||||
|
||||
**Decision for this scaffold:** accept the precision loss. Document it. UI code does not use 64-bit timestamps. If/when a use case demands it, `time_now_utc` can return a `BigInt` and we can introduce a `BigInt` sub-mode. That's a follow-up.
|
||||
|
||||
---
|
||||
|
||||
## 7. What's NOT supported in JS target initially
|
||||
|
||||
This is the canonical list. Programs that use any of these compile (no `#error`-style fail-fast like the C backend's capability check) but throw at runtime or behave as documented.
|
||||
|
||||
| Feature | Status | Notes |
|
||||
|---|---|---|
|
||||
| `cgi {}` block | Compiled to a no-op + warning comment | CGI identity is server-side. UI code is not a CGI. |
|
||||
| `service {}` block | Compiled to a no-op + warning comment | Same. |
|
||||
| All `dharma_*` | Stub throws | Programs needing DHARMA must call a server-side daemon over HTTP |
|
||||
| All `engram_*` | Stub throws | Could be ported to in-browser (IndexedDB-backed) later |
|
||||
| All `llm_*` | Stub throws | Browser cannot hold API keys; route through server |
|
||||
| `llm_register_tool` | Stub throws | Same |
|
||||
| `http_serve` | Stub throws | Browsers cannot serve. Node-mode could, deferred |
|
||||
| `http_set_handler` | Stub throws | Same |
|
||||
| `match` expressions | Compiled (basic) | LitInt/LitStr/LitBool/Wildcard/Binding all work via `if/else` chain. Tagged-union match deferred |
|
||||
| `type` (struct) defs | Skipped at codegen | Treated as documentation; structs are plain JS objects. `t["field"]` works |
|
||||
| `enum` defs | Skipped at codegen | Same — enum values are bare strings or ints |
|
||||
| `?` postfix (nil-prop) | No-op | Same as C backend's current state |
|
||||
| `try` postfix | Stripped to inner | Same as C backend |
|
||||
| Capability enforcement | Not enforced | The C backend uses `#error` directives; the JS backend lets the runtime stubs throw. Future: emit `throw new Error('capability violation')` at compile time |
|
||||
| VBD role check | Not enforced | Same |
|
||||
| Float bit-cast | Not needed | JS number is already a double |
|
||||
| Crypto primitives | Stub throws | Easy to add via `crypto.subtle` later |
|
||||
| `state_*` | In-memory only | No persistence; resets on page reload |
|
||||
| `args()` | Node-only | Browser returns `[]` |
|
||||
| `fs_*` | Node-only | Browser throws |
|
||||
|
||||
---
|
||||
|
||||
## 8. CLI dispatch — `--target=js`
|
||||
|
||||
The compiler entry point `compiler.el` adds a `compile_js(source: String) -> String` alongside the existing `compile()`. The CLI behavior:
|
||||
|
||||
```
|
||||
elc <source.el> <output> # default — emit C
|
||||
elc --target=c <source.el> <out> # explicit — emit C
|
||||
elc --target=js <source.el> <out> # emit JS
|
||||
|
||||
elc --target=js source.el # write JS to stdout (no out path)
|
||||
```
|
||||
|
||||
The argv parser scans for a `--target=<lang>` token; remaining positional args are `<source>` and optional `<out>`. The dispatch logic stays in El: a `compile_dispatch(target, source) -> String` switch.
|
||||
|
||||
---
|
||||
|
||||
## 9. The path to compiling el-ui/runtime through this backend
|
||||
|
||||
This is the real-world test. `el-ui/runtime/src/` is currently 5 hand-written `.js` files. The path to authoring them in El:
|
||||
|
||||
1. **Phase 1 — Hello-world** (this scaffold). Done.
|
||||
2. **Phase 2 — language coverage.** Get codegen-js to ~95% parity with codegen.el for non-network features. Specifically: `match`, struct/enum field access, `?`-propagation, full `for`-over-list, complete unary/binary operators, lexical closures (the C backend doesn't have these but we'll need them for el-ui's component model).
|
||||
3. **Phase 3 — DOM bridge.** Add `dom_*` builtins to el_runtime.js: `dom_create_element`, `dom_set_text`, `dom_append_child`, `dom_query`, `dom_listen`, etc. These are Node-as-El builtins for the browser; the C backend will add a stub set that errors. Source-shareable El UI code becomes possible.
|
||||
4. **Phase 4 — Component class lowering.** El doesn't have classes; el-ui's `Component` is a JS class. Decide: extend El with a `component` keyword that compiles to JS class + C struct? Or have el-ui authors define components as `fn render_<name>(state) -> String` and provide a small bootstrap. The latter is the lower-impact path.
|
||||
5. **Phase 5 — Async taint pass.** Implement compile-time async tracking so `http_get` and friends produce `await fetch()` correctly. Required before authoring code that fetches data.
|
||||
6. **Phase 6 — Port `el-ui/runtime/`.** Translate the 5 JS files to El, compile to JS, swap in. Run el-ui's existing tests. Iterate.
|
||||
7. **Phase 7 — Port cgi-studio UI.** Larger surface area; same pattern.
|
||||
8. **Phase 8 — Marketplace plugins.** Open the door for third-party UI El.
|
||||
|
||||
The blocking item between phase 1 and phase 2 is incremental — every El construct used by el-ui's source needs codegen-js coverage. Phase 5 (async) is the architectural decision that needs explicit user buy-in, because it changes the language's effective semantics on the JS target.
|
||||
|
||||
---
|
||||
|
||||
## 10. Test
|
||||
|
||||
```bash
|
||||
echo 'fn main() -> Void { println("hello from el-js") }' > /tmp/hello.el
|
||||
elc --target=js /tmp/hello.el > /tmp/hello.js
|
||||
node /tmp/hello.js
|
||||
# → hello from el-js
|
||||
```
|
||||
|
||||
This should pass after the bootstrap rebuild. See §11.
|
||||
|
||||
---
|
||||
|
||||
## 11. Bootstrap status
|
||||
|
||||
Adding `--target=js` to `compile()` requires regenerating the shipped `elc` binary at `dist/platform/elc`. The rebuild path is:
|
||||
|
||||
1. Existing `elc` binary compiles updated `elc-combined.el` (which now includes `codegen-js.el` and the `--target=js` dispatch) → `elc.c`.
|
||||
2. `cc` compiles `elc.c` → new `elc` binary.
|
||||
3. New `elc` binary supports `--target=js`.
|
||||
|
||||
The scaffold checks all four scaffold files in. The bootstrap rebuild happens as a follow-up step, gated on review of this design doc.
|
||||
Reference in New Issue
Block a user